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

    Neuronpedia

    INDEX
    Explanations

    Ratios and percentages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    缉
    -0.08
    筮
    -0.07
     гос
    -0.07
     العلاقة
    -0.07
     investigator
    -0.07
    配偶
    -0.07
    IDS
    -0.06
    🆂
    -0.06
     lovers
    -0.06
     InvalidArgumentException
    -0.06
    POSITIVE LOGITS
    :[
    0.07
     bloss
    0.07
    [attr
    0.07
     Console
    0.06
    ,GL
    0.06
    (W
    0.06
    Om
    0.06
    colo
    0.06
    composed
    0.06
     terminals
    0.06
    Act Density 0.062%

    No Known Activations