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

    Neuronpedia

    INDEX
    Explanations

    quantitative measures and statistics

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

    numbers and quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RefNanny
    -0.36
     vyu
    -0.34
    Kariera
    -0.32
     restre
    -0.32
    ições
    -0.32
     events
    -0.32
     זאת
    -0.31
    Véase
    -0.30
    else
    -0.29
     récemment
    -0.29
    POSITIVE LOGITS
    ðsíða
    0.76
    <unused41>
    0.75
    <unused16>
    0.75
    <unused8>
    0.75
    <unused42>
    0.75
    <unused52>
    0.75
    <unused51>
    0.75
    <unused68>
    0.75
    <unused14>
    0.75
    <unused3>
    0.75
    Act Density 0.065%

    No Known Activations