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

    Neuronpedia

    INDEX
    Explanations

    proceed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     "];
    -0.58
    hitheatre
    -0.56
    ristan
    -0.54
     caer
    -0.52
    ็ง
    -0.52
    mgang
    -0.50
    betical
    -0.50
    engers
    -0.49
    tipation
    -0.49
    []"
    -0.49
    POSITIVE LOGITS
     يتيمه
    0.68
    脚注の使い方
    0.68
    GEBURTSDATUM
    0.68
     تانيه
    0.54
     ujednoznacz
    0.52
     with
    0.51
     useStyles
    0.51
    withIdentifier
    0.50
    ApiProperty
    0.49
    estacks
    0.49
    Act Density 0.005%

    No Known Activations