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

    Neuronpedia

    INDEX
    Explanations

    assembly instructions and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    },\
    0.50
    _
    0.45
    ের
    0.43
    一緒に
    0.43
    各自
    0.43
    benzoic
    0.42
    ́
    0.41
    这意味着
    0.41
    ]+\
    0.40
    })+\
    0.40
    POSITIVE LOGITS
     sufrir
    0.52
     страда
    0.51
     stair
    0.50
     Paar
    0.47
     alkene
    0.46
     skillset
    0.46
    COST
    0.46
     NODE
    0.46
     マーク
    0.45
     MIUI
    0.45
    Act Density 0.000%

    No Known Activations