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

    Neuronpedia

    INDEX
    Explanations

    subject and other languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ArrayBox
    0.48
    y
    0.47
    has
    0.44
    வரி
    0.44
    TimeStamp
    0.44
    aspect
    0.42
    Tasks
    0.42
    ಕಾರ
    0.42
    属性
    0.41
    ent
    0.41
    POSITIVE LOGITS
     estoppel
    0.44
     unmittelbar
    0.42
     claras
    0.42
     entste
    0.42
     rinsing
    0.42
     imediatamente
    0.42
     дозво
    0.41
     anderen
    0.41
     permiten
    0.41
     embol
    0.41
    Act Density 0.004%

    No Known Activations