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

    Neuronpedia

    INDEX
    Explanations

    ID

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    okud
    -0.07
     말
    -0.07
    נ
    -0.07
    ερ
    -0.06
    曲
    -0.06
    addon
    -0.06
    Concept
    -0.06
    agog
    -0.06
    ør
    -0.06
    haul
    -0.06
    POSITIVE LOGITS
     ID
    0.10
    >';↵↵
    0.06
     synthetic
    0.06
     PUS
    0.06
    olithic
    0.06
    sha
    0.06
     Number
    0.06
    งก
    0.06
     presumably
    0.06
    .sdk
    0.06
    Act Density 0.021%

    No Known Activations