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

    Neuronpedia

    INDEX
    Explanations

    participants

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     laden
    -0.07
     obscene
    -0.06
    Hundreds
    -0.06
    ISTICS
    -0.06
     Officers
    -0.06
     befind
    -0.06
    อพ
    -0.06
    Ố
    -0.06
    ěr
    -0.06
     '-',
    -0.06
    POSITIVE LOGITS
    temperature
    0.08
    defer
    0.07
     topical
    0.07
    knowledge
    0.07
     funct
    0.06
    Url
    0.06
     Wisdom
    0.06
     вив
    0.06
    .setContent
    0.06
    bare
    0.06
    Act Density 0.000%

    No Known Activations