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

    Neuronpedia

    INDEX
    Explanations

    compound interest, exponential growth, snowball effect

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     furnished
    0.43
     பொழுது
    0.41
     vorhanden
    0.40
     enumerated
    0.39
     proffered
    0.38
    埓
    0.38
     entertained
    0.38
     собою
    0.38
     presented
    0.38
     harbor
    0.38
    POSITIVE LOGITS
     exponentially
    0.85
     exponential
    0.82
    exponential
    0.78
    Exponential
    0.76
     Exponential
    0.74
     exponencial
    0.73
     snowball
    0.56
    曲线
    0.53
    指数
    0.52
    雪
    0.51
    Act Density 0.000%

    No Known Activations