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

    Neuronpedia

    INDEX
    Explanations

    Azure AD Connect

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bandingan
    0.82
    捗
    0.81
    emmel
    0.76
    綪
    0.74
    жная
    0.72
    Entered
    0.72
    efficient
    0.70
     ang
    0.68
    SWE
    0.68
    イベント
    0.68
    POSITIVE LOGITS
     lancer
    0.87
     Rowing
    0.79
    Row
    0.78
     settle
    0.75
     row
    0.73
    row
    0.71
    aptops
    0.71
     atto
    0.70
    शीलता
    0.70
    though
    0.70
    Act Density 0.000%

    No Known Activations