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

    Neuronpedia

    INDEX
    Explanations

    actions and related concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    attacks
    0.48
    instance
    0.47
    index
    0.47
    from
    0.46
    onio
    0.46
     ataques
    0.45
    bica
    0.42
    ove
    0.41
    icano
    0.41
    zsche
    0.41
    POSITIVE LOGITS
     Restricted
    0.47
     clientele
    0.47
     Athletics
    0.45
     anne
    0.43
     Valentine
    0.42
     біль
    0.42
     Anne
    0.42
     Johnny
    0.41
     restricted
    0.41
     Remembrance
    0.40
    Act Density 0.003%

    No Known Activations