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

    Neuronpedia

    INDEX
    Explanations

    it

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     latch
    -0.07
     wool
    -0.06
    antor
    -0.06
     sektör
    -0.06
     axes
    -0.06
    ose
    -0.06
    鑑
    -0.06
    _pause
    -0.06
    	pw
    -0.06
    inbox
    -0.06
    POSITIVE LOGITS
     Taco
    0.07
    죽
    0.06
    стра
    0.06
    DispatchToProps
    0.06
    ivement
    0.06
     festivities
    0.06
    еться
    0.06
    _walk
    0.06
     अभ
    0.06
     Одна
    0.06
    Act Density 0.281%

    No Known Activations