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

    Neuronpedia

    INDEX
    Explanations

    therapy sessions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Finalize
    -0.09
    േറ്റ്
    -0.08
    -Test
    -0.08
     shortlist
    -0.08
    /Test
    -0.08
    justice
    -0.08
     završ
    -0.08
    legacy
    -0.08
    ście
    -0.08
     Justice
    -0.08
    POSITIVE LOGITS
     projections
    0.09
     projecting
    0.09
    $arity
    0.08
     projection
    0.08
     ...↵↵
    0.08
     bund
    0.08
    吊
    0.08
     વધ
    0.08
     projector
    0.08
     чоң
    0.08
    Act Density 0.003%

    No Known Activations