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

    Neuronpedia

    INDEX
    Explanations

    project descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    рити
    -0.08
     查
    -0.07
    alendar
    -0.07
     Snyder
    -0.06
    070
    -0.06
    <Message
    -0.06
    ентами
    -0.06
    amment
    -0.06
    nowledge
    -0.06
     Yo
    -0.06
    POSITIVE LOGITS
     K
    0.11
    .K
    0.10
    KO
    0.10
    K
    0.10
     king
    0.10
     KS
    0.09
    KEY
    0.09
     KA
    0.09
     Key
    0.09
    *K
    0.09
    Act Density 0.547%

    No Known Activations