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

    Neuronpedia

    INDEX
    Explanations

    less

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iej
    -0.07
     Ukraj
    -0.06
     tồn
    -0.06
    BG
    -0.06
    ฑ
    -0.06
    edian
    -0.06
    .Transform
    -0.06
     Realty
    -0.06
    struments
    -0.06
    -assets
    -0.06
    POSITIVE LOGITS
     hunger
    0.07
    essenger
    0.07
    ALTH
    0.07
    LESS
    0.07
     �
    0.06
     adjunct
    0.06
    AGER
    0.06
     CRE
    0.06
     درب
    0.06
    сыл
    0.06
    Act Density 0.002%

    No Known Activations