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

    Neuronpedia

    INDEX
    Explanations

    special characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ANE
    -0.07
     circuits
    -0.07
    akers
    -0.07
    ramento
    -0.06
    	State
    -0.06
     순간
    -0.06
    ств
    -0.06
    证明
    -0.06
    ustralia
    -0.06
    	group
    -0.06
    POSITIVE LOGITS
     масла
    0.07
     squeeze
    0.07
    cascade
    0.07
     (?
    0.07
    ฉ
    0.06
    (predicate
    0.06
     прест
    0.06
    .AF
    0.06
    зація
    0.06
     kodu
    0.06
    Act Density 0.040%

    No Known Activations