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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     unchecked
    -0.07
    (rec
    -0.07
    пи
    -0.07
     kids
    -0.06
    Self
    -0.06
     police
    -0.06
     probe
    -0.06
    Credential
    -0.06
     felony
    -0.06
    EF
    -0.06
    POSITIVE LOGITS
     cyt
    0.08
    装置
    0.07
    /ac
    0.07
     jsonObj
    0.07
     CheckBox
    0.07
    라인
    0.07
     _$
    0.07
    _GC
    0.06
    ->{'
    0.06
    _Close
    0.06
    Act Density 0.008%

    No Known Activations