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

    Neuronpedia

    INDEX
    Explanations

    color

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    abilia
    -0.07
     Benjamin
    -0.07
     �
    -0.07
    Wil
    -0.07
    bx
    -0.06
     оброб
    -0.06
     GDK
    -0.06
     устрой
    -0.06
    Hen
    -0.06
     prosecutor
    -0.06
    POSITIVE LOGITS
     Nature
    0.07
    แหล
    0.06
     climbing
    0.06
     giành
    0.06
    _years
    0.06
     doom
    0.06
     COVID
    0.06
    ảng
    0.06
    (selector
    0.06
    -East
    0.06
    Act Density 0.007%

    No Known Activations