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

    Neuronpedia

    INDEX
    Explanations

    identity protection

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    üler
    -0.06
     porter
    -0.06
     я
    -0.06
    +N
    -0.06
     LOCATION
    -0.06
    Honda
    -0.06
     आस
    -0.06
     snapchat
    -0.06
     green
    -0.06
     Dash
    -0.06
    POSITIVE LOGITS
    ाड
    0.07
    ,input
    0.06
    .scal
    0.06
    predictions
    0.06
    нез
    0.06
    (this
    0.06
     thức
    0.06
    :"-
    0.06
    .observable
    0.06
     долго
    0.06
    Act Density 0.023%

    No Known Activations