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

    Neuronpedia

    INDEX
    Explanations

    column

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Nil
    0.61
    Roe
    0.57
    േയ
    0.56
     facilitate
    0.54
     Fontainebleau
    0.54
     nil
    0.54
     clarify
    0.54
     Roe
    0.53
    ⌐
    0.53
    aliya
    0.52
    POSITIVE LOGITS
    umn
    1.14
    umna
    1.02
    umno
    0.97
    UMN
    0.95
    ums
    0.76
    umen
    0.76
    umm
    0.71
    oured
    0.69
    UMNS
    0.68
     um
    0.68
    Act Density 0.000%

    No Known Activations