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

    Neuronpedia

    INDEX
    Explanations

    ARISING

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ATTERY
    -0.06
    允
    -0.06
    errs
    -0.06
    .controllers
    -0.06
     순
    -0.06
     opět
    -0.06
    갔다
    -0.06
    媒
    -0.06
    CLUS
    -0.06
    َع
    -0.06
    POSITIVE LOGITS
     ARISING
    0.11
     arising
    0.09
    peq
    0.07
     Delaware
    0.07
     Convenience
    0.07
    ват
    0.07
    kb
    0.06
     Princeton
    0.06
     ReturnValue
    0.06
    [current
    0.06
    Act Density 0.001%

    No Known Activations