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

    Neuronpedia

    INDEX
    Explanations

    financial statement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ED
    0.49
    _
    0.47
    c
    0.47
    k
    0.46
    RC
    0.46
    e
    0.45
    an
    0.45
    .
    0.45
    o
    0.45
     toro
    0.44
    POSITIVE LOGITS
    اسلام
    0.54
     cartão
    0.51
    ጳ
    0.50
     తయ
    0.49
     পাঠকের
    0.48
     antagonists
    0.48
     checklists
    0.47
     Osmanlı
    0.47
     blockers
    0.47
     Terraform
    0.46
    Act Density 0.000%

    No Known Activations