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

    Neuronpedia

    INDEX
    Explanations

    addresses and locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    x
    0.73
     studente
    0.68
     obiettivo
    0.67
     ataque
    0.65
    ↵↵
    0.64
     coleta
    0.59
    д
    0.59
     ilyen
    0.57
    ad
    0.54
     Após
    0.54
    POSITIVE LOGITS
    0.66
     pergola
    0.63
     boulevard
    0.62
    haven
    0.61
    س
    0.61
     garden
    0.61
    橋
    0.61
    ৫
    0.60
    Park
    0.59
    Port
    0.59
    Act Density 0.394%

    No Known Activations