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

    Neuronpedia

    INDEX
    Explanations

    prior events or sequencing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    If
    0.72
    如果您
    0.71
    Especially
    0.70
    Created
    0.68
    #[
    0.67
    Hvis
    0.67
    So
    0.67
    Not
    0.66
    Because
    0.65
    И
    0.65
    POSITIVE LOGITS
     they
    1.34
     it
    1.10
     being
    0.89
     she
    0.87
     its
    0.83
     he
    0.82
     we
    0.81
     realizing
    0.75
     ĝi
    0.74
     они
    0.73
    Act Density 0.083%

    No Known Activations