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

    Neuronpedia

    INDEX
    Explanations

    verb + particle phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IZED
    0.79
    ALLY
    0.74
    IZING
    0.74
     Pentec
    0.74
    ized
    0.72
    る
    0.72
    чних
    0.72
    iseerd
    0.72
    чными
    0.71
    itatively
    0.70
    POSITIVE LOGITS
    outs
    2.07
    out
    1.98
    ups
    1.97
    up
    1.93
    offs
    1.81
     offs
    1.74
    off
    1.72
    backs
    1.69
    away
    1.67
    aways
    1.65
    Act Density 0.444%

    No Known Activations