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

    Neuronpedia

    INDEX
    Explanations

    Hypothetical situations

    np_max-act · gemini-2.0-flash

    This neuron detects passive‐voice constructions, i.e. forms of “be” (had, been, is) combined with a past participle.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    016
    -0.07
     ---------
    -0.07
     outs
    -0.07
    ctl
    -0.07
    ิพ
    -0.07
    Detail
    -0.06
     '@/
    -0.06
    95
    -0.06
    薩
    -0.06
    014
    -0.06
    POSITIVE LOGITS
    (substr
    0.07
     редак
    0.06
     움
    0.06
    RAIN
    0.06
    .birth
    0.06
    .row
    0.06
    (mut
    0.06
     火
    0.06
    .LookAndFeel
    0.06
     qualidade
    0.06
    Act Density 0.013%

    No Known Activations