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

    Neuronpedia

    INDEX
    Explanations

    counting, listing, and career context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tensor
    0.38
     dodgy
    0.37
    الك
    0.37
    0.37
    ){\
    0.37
    橢
    0.36
    阿
    0.36
    欧
    0.36
     fontWeight
    0.35
    考試
    0.35
    POSITIVE LOGITS
    ayu
    0.46
    PTION
    0.43
     ይህ
    0.41
    ımı
    0.40
    gga
    0.38
    emberg
    0.38
    inoza
    0.38
     maneuver
    0.38
     Congrats
    0.38
     poderoso
    0.38
    Act Density 0.000%

    No Known Activations