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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _bool
    -0.08
     entityId
    -0.07
    %\
    -0.07
    /**
    -0.06
    AC
    -0.06
     jedoch
    -0.06
    opak
    -0.06
     �
    -0.06
     Fet
    -0.06
     případech
    -0.06
    POSITIVE LOGITS
                                 ↵
    0.07
     Lucy
    0.06
    >>(↵
    0.06
    eny
    0.06
    _sun
    0.06
    bracht
    0.06
     ліс
    0.06
     authoritarian
    0.06
                             ↵
    0.06
     Bộ
    0.06
    Act Density 0.080%

    No Known Activations