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

    Neuronpedia

    INDEX
    Explanations

    Games

    np_max-act · gemini-2.0-flash

    The neuron never activates on any input tokens—i.e. it is essentially “dead” and does not respond to any text pattern.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    WEEN
    -0.07
     stability
    -0.07
    746
    -0.07
    .put
    -0.06
    _resume
    -0.06
    -A
    -0.06
    ّة
    -0.06
     synagogue
    -0.06
    Ε
    -0.06
    Titles
    -0.06
    POSITIVE LOGITS
     podnikatel
    0.07
     тол
    0.07
    Nİ
    0.07
    ceptar
    0.06
     ['',
    0.06
    abal
    0.06
    [model
    0.06
     таблет
    0.06
     سالم
    0.06
    vangst
    0.06
    Act Density 0.102%

    No Known Activations