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

    Neuronpedia

    INDEX
    Explanations

    call

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Biom
    -0.07
     biom
    -0.07
     ACLU
    -0.07
     �
    -0.07
     PROP
    -0.06
     Brennan
    -0.06
     gou
    -0.06
     Analyzer
    -0.06
     lut
    -0.06
     �
    -0.06
    POSITIVE LOGITS
    Instant
    0.07
    玩
    0.07
    问题
    0.07
    сер
    0.06
     resources
    0.06
     officials
    0.06
    ffi
    0.06
    groupName
    0.06
    -story
    0.06
    -mort
    0.06
    Act Density 0.016%

    No Known Activations