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

    Neuronpedia

    INDEX
    Explanations

    reasons and answers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    etc
    0.80
    labelledby
    0.74
    才能
    0.72
    などが
    0.72
    などに
    0.71
    などを
    0.70
     сможете
    0.69
     etc
    0.69
    等が
    0.69
    等を
    0.68
    POSITIVE LOGITS
    .
    1.26
    ;
    1.20
    !
    1.19
    <unused2190>
    1.18
    :
    1.10
    。
    1.09
    .;
    1.09
    ؛
    1.05
    ™.
    1.04
    ፡፡
    1.04
    Act Density 0.139%

    No Known Activations