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

    Neuronpedia

    INDEX
    Explanations

    limits and quantifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     corredor
    0.40
    elage
    0.37
    iddag
    0.37
    Bi
    0.36
    Trigger
    0.36
    Vill
    0.35
    Strip
    0.34
    IAM
    0.34
    दित
    0.33
    道
    0.33
    POSITIVE LOGITS
    onomie
    0.43
     incon
    0.43
     ambivalent
    0.42
     раст
    0.40
    onom
    0.40
    配置文件
    0.40
     mantras
    0.39
    ക്കാ
    0.39
     impatient
    0.39
     pathos
    0.39
    Act Density 0.000%

    No Known Activations