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

    Neuronpedia

    INDEX
    Explanations

    interest rate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wore
    0.42
     অর্থাৎ
    0.41
     ceases
    0.41
     թվական
    0.40
     воз
    0.39
     सर्व
    0.39
     yerine
    0.39
    米的
    0.38
     donné
    0.38
     yoki
    0.38
    POSITIVE LOGITS
    divid
    0.46
    How
    0.43
    snow
    0.40
    during
    0.40
    Proble
    0.40
    blower
    0.39
     How
    0.39
    yet
    0.38
    bergh
    0.37
    lov
    0.36
    Act Density 0.000%

    No Known Activations