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

    Neuronpedia

    INDEX
    Explanations

    slightly, bile reflux, subtle presence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ię
    2.08
    ać
    2.05
    iak
    2.03
    มัน
    1.98
    ea
    1.96
    pp
    1.95
    ge
    1.94
    aal
    1.93
    yor
    1.91
     poiché
    1.89
    POSITIVE LOGITS
    ка
    2.91
    いた
    2.91
    о
    2.48
    ان
    2.44
    ून
    2.39
    न
    2.31
    います
    2.22
    ন
    2.20
    од
    2.06
    ছেন
    2.05
    Act Density 0.945%

    No Known Activations