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

    Neuronpedia

    INDEX
    Explanations

    code metadata

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     response
    -0.08
     міс
    -0.07
     Careers
    -0.07
     analý
    -0.06
     Payment
    -0.06
     repayment
    -0.06
    /|
    -0.06
     Mixing
    -0.06
     рівень
    -0.06
    .variables
    -0.06
    POSITIVE LOGITS
    appId
    0.07
     �
    0.07
    .onclick
    0.06
    Jay
    0.06
    /messages
    0.06
    UT
    0.06
    productId
    0.06
     parchment
    0.06
    icut
    0.06
    umph
    0.06
    Act Density 0.010%

    No Known Activations