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

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal growth and support

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

    achieved with confidence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    равда
    -0.56
     spesielt
    -0.54
     appunto
    -0.54
     nemlig
    -0.52
     principalement
    -0.52
     zejména
    -0.52
    Enllaces
    -0.51
     purtroppo
    -0.51
     supuestamente
    -0.51
     fameux
    -0.51
    POSITIVE LOGITS
     with
    0.69
     yourself
    0.63
     today
    0.58
     tomorrow
    0.50
     tonight
    0.49
    with
    0.47
     without
    0.46
     easily
    0.45
     using
    0.45
    With
    0.43
    Act Density 0.023%

    No Known Activations