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

    Neuronpedia

    INDEX
    Explanations

    Multiple languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     praised
    -0.07
    [SerializeField
    -0.07
    Different
    -0.07
     Poison
    -0.06
    .Please
    -0.06
     neuron
    -0.06
     touching
    -0.06
    panel
    -0.06
     yt
    -0.06
    _ln
    -0.06
    POSITIVE LOGITS
     hookers
    0.08
    	Send
    0.06
    Estado
    0.06
     Took
    0.06
     台
    0.06
     Evet
    0.06
    .onStart
    0.06
    .breakpoints
    0.06
    _community
    0.06
     Voldemort
    0.06
    Act Density 0.002%

    No Known Activations