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

    Neuronpedia

    INDEX
    Explanations

    prefixes for descriptive words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    на
    0.70
    ic
    0.69
    ua
    0.68
    та
    0.68
    ov
    0.67
    UT
    0.64
    ens
    0.63
    us
    0.63
    ۵
    0.62
    iv
    0.62
    POSITIVE LOGITS
    ，
    0.52
    ।
    0.51
    。
    0.49
    <
    0.49
    ↵↵
    0.47
    0.47
     individu
    0.46
     out
    0.45
     streng
    0.44
    以下
    0.42
    Act Density 0.261%

    No Known Activations