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

    Neuronpedia

    INDEX
    Explanations

    if not for, if not, what if

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ್‌
    2.04
    িল
    1.88
    ter
    1.81
    י
    1.78
    d
    1.77
    en
    1.72
     anno
    1.69
    чего
    1.68
     voet
    1.68
     odw
    1.66
    POSITIVE LOGITS
     propensity
    2.06
    方法
    1.94
    ()=>{
    1.85
    ี้
    1.79
    poder
    1.77
     mites
    1.77
    sommets
    1.76
    க
    1.70
    分区
    1.70
    ために
    1.66
    Act Density 0.007%

    No Known Activations