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

    Neuronpedia

    INDEX
    Explanations

    .utils

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     exhibiting
    -0.08
    emake
    -0.08
    UMA
    -0.08
     Personally
    -0.08
    -era
    -0.07
     ร
    -0.07
     bản
    -0.07
     TED
    -0.07
    -0.07
     subcon
    -0.07
    POSITIVE LOGITS
     oil
    0.08
     oils
    0.08
     ay
    0.08
     виз
    0.07
     sn
    0.07
     Ih
    0.07
     ASE
    0.07
     sticks
    0.07
     stick
    0.07
    oil
    0.07
    Act Density 0.002%
    No Known Activations