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

    Neuronpedia

    INDEX
    Explanations

    lic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    áním
    -0.08
     prin
    -0.07
     مکان
    -0.06
    ováním
    -0.06
     под
    -0.06
    بری
    -0.06
     Nr
    -0.06
     ethnic
    -0.06
     stupidity
    -0.06
     연
    -0.06
    POSITIVE LOGITS
    room
    0.07
    ripe
    0.07
     Roberts
    0.06
    全部
    0.06
    ivil
    0.06
     McDonald
    0.06
    вит
    0.06
    PTION
    0.06
    .encrypt
    0.06
    quiry
    0.06
    Act Density 0.010%

    No Known Activations