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

    Neuronpedia

    INDEX
    Explanations

    statistics and information related to health risks and medical conditions

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

    increase of probability or risk

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    hlí
    -0.41
     risol
    -0.39
    cetype
    -0.38
    enderror
    -0.38
     sottile
    -0.37
     zacht
    -0.36
     Publicar
    -0.36
     dozen
    -0.36
    feras
    -0.36
     tiny
    -0.35
    POSITIVE LOGITS
    Increased
    0.77
     increased
    0.75
     Increased
    0.75
    increased
    0.72
    Increase
    0.63
     Increasing
    0.63
    Increasing
    0.60
     Increase
    0.60
     increase
    0.58
    IsMutable
    0.54
    Act Density 0.250%

    No Known Activations