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

    Neuronpedia

    INDEX
    Explanations

    states or explains

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     says
    0.88
    says
    0.77
     said
    0.75
     говорит
    0.73
     sagt
    0.67
    Says
    0.66
     säger
    0.65
     zegt
    0.61
    said
    0.60
     कहता
    0.60
    POSITIVE LOGITS
     pointed
    0.72
    pointed
    0.67
     pointing
    0.65
     apont
    0.64
    Pointing
    0.64
     mus
    0.63
     noted
    0.60
     noting
    0.59
    elabor
    0.59
    pointing
    0.56
    Act Density 0.000%

    No Known Activations