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

    Neuronpedia

    INDEX
    Explanations

    active

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     نوش
    -0.07
     indebted
    -0.06
     Expanded
    -0.06
    ro
    -0.06
    ographers
    -0.06
     يس
    -0.06
     nue
    -0.06
     irre
    -0.06
     expenses
    -0.06
    _system
    -0.06
    POSITIVE LOGITS
    245
    0.07
    -key
    0.07
    lectual
    0.06
    (View
    0.06
     MUST
    0.06
    (COM
    0.06
    募
    0.06
    51
    0.05
    xEE
    0.05
     fauna
    0.05
    Act Density 0.004%

    No Known Activations