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

    Neuronpedia

    INDEX
    Explanations

    and,

    np_max-act · gemini-2.0-flash

    This neuron is effectively “dead” — it never activates and thus does not detect any particular pattern.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Kashmir
    -0.06
    év
    -0.06
     eer
    -0.06
     meer
    -0.06
    apeutics
    -0.06
     Hat
    -0.06
    -Muslim
    -0.06
    Critical
    -0.06
    мовір
    -0.06
    .metroLabel
    -0.06
    POSITIVE LOGITS
     PL
    0.06
     puppet
    0.06
    _and
    0.06
    	prop
    0.06
     fais
    0.06
    YG
    0.06
    нулся
    0.06
     governing
    0.06
     racket
    0.06
     sized
    0.06
    Act Density 0.043%

    No Known Activations