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

    Neuronpedia

    INDEX
    Explanations

    papers

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is pick out academic‐publishing terms—i.e. mentions of journal activity or article types (papers, reviews, communications, etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ")+
    -0.06
    号
    -0.06
     अलग
    -0.06
    omit
    -0.06
     ohne
    -0.06
     últ
    -0.06
    NEL
    -0.06
    "":
    -0.05
    @click
    -0.05
     항
    -0.05
    POSITIVE LOGITS
    (GL
    0.07
     cloth
    0.07
    .Tasks
    0.07
     Athe
    0.06
    ("(%
    0.06
     couleur
    0.06
    _scene
    0.06
    .DataGridViewCellStyle
    0.06
    programs
    0.06
    -family
    0.06
    Act Density 0.012%

    No Known Activations