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

    Neuronpedia

    INDEX
    Explanations

    pronoun followed by verb or possessive

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    as
    0.72
    on
    0.63
    م
    0.62
    is
    0.59
    um
    0.59
    ्यून
    0.56
     végétaux
    0.55
    X
    0.55
    aml
    0.54
    Estamos
    0.54
    POSITIVE LOGITS
    他的
    0.72
     himself
    0.71
    0.69
     statesmen
    0.62
     صلى
    0.61
     his
    0.60
     Majesty
    0.59
    mming
    0.58
    0.58
     получил
    0.56
    Act Density 0.280%

    No Known Activations