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

    Neuronpedia

    INDEX
    Explanations

    explain or describe

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    💏
    0.69
    кам
    0.64
    hender
    0.63
     Simultaneous
    0.59
     FEM
    0.58
     )),
    0.57
    FEM
    0.57
    }[!
    0.57
    gages
    0.57
    imedia
    0.55
    POSITIVE LOGITS
     over
    0.73
     አሉ
    0.65
    Over
    0.64
     Over
    0.63
     saranno
    0.61
     flamb
    0.60
     mau
    0.59
     خواهند
    0.57
    over
    0.56
    庆祝
    0.55
    Act Density 0.000%

    No Known Activations