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

    Neuronpedia

    INDEX
    Explanations

    parenthetical explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    jenigen
    0.38
    Describes
    0.38
     proposes
    0.37
    uillez
    0.36
    }'.
    0.35
     identifies
    0.35
    떤
    0.35
     adver
    0.35
    }}\
    0.34
    ieniu
    0.34
    POSITIVE LOGITS
     बेशक
    0.57
     όχι
    0.54
    seriously
    0.53
     Yes
    0.53
     настолько
    0.53
     Seriously
    0.52
     особенно
    0.51
     Honestly
    0.51
    简直
    0.51
    もちろん
    0.51
    Act Density 0.146%

    No Known Activations