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

    Neuronpedia

    INDEX
    Explanations

    red

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _updated
    -0.07
    buttons
    -0.07
     barrier
    -0.06
     TableName
    -0.06
     sanitary
    -0.06
     Cyan
    -0.06
    -0.06
    cyan
    -0.06
     dl
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     DISP
    0.08
     Experiment
    0.07
    lamış
    0.07
     suspect
    0.07
     Haz
    0.07
    .ac
    0.07
    (existing
    0.06
     Aspect
    0.06
    oulos
    0.06
     Gobierno
    0.06
    Act Density 0.003%

    No Known Activations