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

    Neuronpedia

    INDEX
    Explanations

    unable to proceed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _action
    -0.08
    _proc
    -0.07
     realistic
    -0.07
    (actions
    -0.07
    .Workflow
    -0.07
    (action
    -0.07
    .Reader
    -0.07
    _logging
    -0.07
    .analytics
    -0.07
     action
    -0.07
    POSITIVE LOGITS
    stellungen
    0.09
    ייה
    0.09
     Sip
    0.08
    atisfactory
    0.08
     მშ
    0.08
     Debido
    0.08
     wela
    0.08
     প্রস্তু
    0.08
     ಸಂಗ
    0.08
     kot
    0.08
    Act Density 0.005%

    No Known Activations