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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash

    This neuron never activates on any tokens—it’s effectively a dead (unused) neuron that doesn’t detect any feature.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     contributions
    -0.08
    áhnout
    -0.07
     reporting
    -0.07
     thirteen
    -0.06
     transition
    -0.06
     contribution
    -0.06
     ост
    -0.06
     optimal
    -0.06
     Trem
    -0.06
    _post
    -0.06
    POSITIVE LOGITS
    ¾
    0.08
    ½
    0.08
     �
    0.08
    ICI
    0.07
     half
    0.07
    ัดการ
    0.07
     beberapa
    0.07
    ctica
    0.06
    /her
    0.06
     discriminate
    0.06
    Act Density 0.011%

    No Known Activations