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

    Neuronpedia

    INDEX
    Explanations

    float and floating-point numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     frente
    3.07
    ו
    3.05
    ra
    2.86
    ва
    2.72
     verso
    2.69
     hör
    2.68
     joué
    2.64
     transformación
    2.63
    вача
    2.56
    s
    2.55
    POSITIVE LOGITS
    ActionButton
    3.53
    parseFloat
    3.20
    ammatory
    3.19
    ванням
    3.16
    ר
    2.96
    නය
    2.93
    ()=>{
    2.82
    дт
    2.76
    ysts
    2.76
    р
    2.73
    Act Density 0.018%

    No Known Activations