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

    Neuronpedia

    INDEX
    Explanations

    ginger paste

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ᓐ
    0.50
     alphan
    0.47
     actuation
    0.46
     optimization
    0.44
     যখন
    0.44
    創
    0.42
    頃
    0.42
    besondere
    0.42
     econom
    0.41
     agitation
    0.41
    POSITIVE LOGITS
    MOBILE
    0.48
     duž
    0.47
    ্যাথ
    0.47
    TRANSFER
    0.46
     Thoreau
    0.46
    Ry
    0.46
    ви
    0.44
    ಟ್‌
    0.44
     soldado
    0.44
    ?/
    0.44
    Act Density 0.007%

    No Known Activations