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

    Neuronpedia

    INDEX
    Explanations

    job descriptions and details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝘺
    0.57
     ump
    0.55
     activar
    0.55
    眦
    0.54
     رمی
    0.52
     eases
    0.52
     शर
    0.51
     facilidad
    0.51
     enzim
    0.51
     noin
    0.50
    POSITIVE LOGITS
     Report
    0.49
     Business
    0.48
    分之一
    0.48
     Times
    0.47
    to
    0.46
    Residential
    0.45
    中
    0.44
    frost
    0.44
    fant
    0.44
     Trade
    0.43
    Act Density 0.000%

    No Known Activations