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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    POINT
    -0.07
    evaluation
    -0.07
     rotor
    -0.06
    (groups
    -0.06
     را
    -0.06
     obey
    -0.06
     coefficients
    -0.06
    _engine
    -0.06
     trois
    -0.06
    calculate
    -0.06
    POSITIVE LOGITS
     indoor
    0.07
     Artifact
    0.06
     Lar
    0.06
    笔
    0.06
     Driving
    0.06
    .anchor
    0.06
     thoải
    0.06
    필
    0.06
     realism
    0.06
     confuse
    0.06
    Act Density 0.056%

    No Known Activations