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

    Neuronpedia

    INDEX
    Explanations

    "whatever you want to call"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     conf
    -0.07
    创
    -0.07
    ํ
    -0.06
    Home
    -0.06
     STREAM
    -0.06
     dört
    -0.06
    atham
    -0.06
    就会
    -0.06
    )↵
    -0.06
     SAT
    -0.06
    POSITIVE LOGITS
    (rv
    0.07
    //=
    0.07
     brunette
    0.06
    .descripcion
    0.06
    Delay
    0.06
     curled
    0.06
    ATORY
    0.06
     initialize
    0.06
    icients
    0.06
     �
    0.06
    Act Density 0.007%

    No Known Activations