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

    Neuronpedia

    INDEX
    Explanations

    descriptive titles and labels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     పుష్
    0.42
    +}$,
    0.42
     اعتبار
    0.39
    Telemetry
    0.39
    UB
    0.39
    Visibility
    0.38
    NodeType
    0.38
     gravel
    0.38
    Yard
    0.38
    犯
    0.38
    POSITIVE LOGITS
    ле
    0.50
    しょ
    0.50
    ப்பட
    0.48
     मे
    0.47
    谣
    0.47
    協
    0.47
    те
    0.47
    फर्म
    0.45
     ಪಡೆ
    0.45
     TITLE
    0.45
    Act Density 0.000%

    No Known Activations