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

    Neuronpedia

    INDEX
    Explanations

    timber and cattle

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     as
    1.40
    л
    1.23
    м
    1.09
    ك
    0.98
    д
    0.91
    š
    0.91
    ด
    0.84
    েন
    0.83
    з
    0.83
     that
    0.82
    POSITIVE LOGITS
    atakse
    0.95
    らの
    0.92
     commenters
    0.89
    ิ
    0.88
    ię
    0.88
    elik
    0.86
     felled
    0.86
     insecticides
    0.85
     الجنس
    0.84
     Elektrokh
    0.84
    Act Density 0.052%

    No Known Activations