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

    Neuronpedia

    INDEX
    Explanations

    symbolism and representation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ä
    0.49
     researching
    0.47
     शुरूआत
    0.46
     copywriting
    0.46
    information
    0.46
     thermodynamics
    0.46
    locking
    0.46
     supermarkets
    0.46
     sensors
    0.45
     मानव
    0.45
    POSITIVE LOGITS
     Symbol
    0.63
     simbolo
    0.61
    Symbol
    0.59
     symbol
    0.57
     simbol
    0.56
     Symbols
    0.56
     симво
    0.55
     Frü
    0.55
    _
    0.54
     symbolically
    0.53
    Act Density 0.110%

    No Known Activations