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

    Neuronpedia

    INDEX
    Explanations

    abstract types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     energy
    0.44
     morphology
    0.43
     bears
    0.42
     descriptions
    0.41
     trumpet
    0.41
     torture
    0.40
     description
    0.40
     journey
    0.40
     voyage
    0.40
     coordinates
    0.39
    POSITIVE LOGITS
    ambito
    0.47
    faulse
    0.46
    fread
    0.44
    বিহার
    0.42
    uchos
    0.42
     বিশেষজ্ঞ
    0.41
    擠
    0.41
    FFEE
    0.41
    щик
    0.40
    estrian
    0.40
    Act Density 0.003%

    No Known Activations