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

    Neuronpedia

    INDEX
    Explanations

    job responsibilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Regeln
    0.42
     useless
    0.39
     معاملہ
    0.37
     tokenId
    0.36
    곱
    0.36
     regola
    0.36
     regras
    0.36
     tanh
    0.36
    MessageNow
    0.35
     utile
    0.35
    POSITIVE LOGITS
    Responsibilities
    1.30
     duties
    1.20
     Duties
    1.20
     respons
    1.17
     Qualifications
    1.16
    Duties
    1.11
    Qualifications
    1.10
     qualifications
    1.09
     Respons
    1.09
    职责
    1.00
    Act Density 0.025%

    No Known Activations