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

    Neuronpedia

    INDEX
    Explanations

    measurements and quantities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Handling
    -0.06
    icone
    -0.06
     cooked
    -0.06
    觉得
    -0.06
     lecturer
    -0.06
    前に
    -0.06
    RequiredMixin
    -0.06
     Car
    -0.06
    	cf
    -0.06
     magic
    -0.06
    POSITIVE LOGITS
    (CharSequence
    0.07
     Biological
    0.07
    ,:,:
    0.07
    +b
    0.07
    _ASSIGN
    0.07
    Ré
    0.07
    _FRONT
    0.06
    \<^
    0.06
     FIRST
    0.06
    ussion
    0.06
    Act Density 0.052%

    No Known Activations