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

    Neuronpedia

    INDEX
    Explanations

    push

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    artifact
    -0.06
     deutschland
    -0.06
    pellier
    -0.06
     Oh
    -0.06
    üssen
    -0.06
     springs
    -0.06
     sal
    -0.06
     Mama
    -0.06
     canc
    -0.06
     맥
    -0.06
    POSITIVE LOGITS
    OWNER
    0.07
    ickness
    0.07
     Prod
    0.06
     *,
    0.06
    (meta
    0.06
     assisted
    0.06
    algo
    0.06
    (proxy
    0.06
    xEB
    0.06
    Prod
    0.06
    Act Density 0.001%

    No Known Activations