Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to prominent figures and their actions or characteristics in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows a personal or professional name

    np_acts-logits-general · gemini-2.0-flash

    he deserved

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aronder
    -0.57
     melihat
    -0.51
     szerint
    -0.51
    */;
    -0.49
    рги
    -0.49
    ingual
    -0.48
    believe
    -0.46
    umeur
    -0.46
     wondering
    -0.45
    eaways
    -0.45
    POSITIVE LOGITS
    AxisAlignment
    0.78
     deserved
    0.74
     deserve
    0.66
     appear
    0.65
     surla
    0.64
    writeField
    0.64
    appear
    0.64
     appears
    0.62
     deserves
    0.62
    .*")]
    0.59
    Act Density 0.548%

    No Known Activations