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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     prejud
    -0.08
    Lemma
    -0.07
     interventions
    -0.06
     Editors
    -0.06
     SUPER
    -0.06
     panc
    -0.06
    PREC
    -0.06
     tragedies
    -0.06
    .writer
    -0.06
     bilir
    -0.06
    POSITIVE LOGITS
    šk
    0.07
    stylesheet
    0.06
    _u
    0.06
     kos
    0.06
     Ames
    0.06
    radouro
    0.06
    主任
    0.06
     WhatsApp
    0.06
    ��
    0.06
     userModel
    0.06
    Act Density 0.022%

    No Known Activations