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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    trash
    -0.06
    vající
    -0.06
     logfile
    -0.06
    持续
    -0.06
     대표
    -0.06
    severity
    -0.06
     ]
↵
    -0.06
     ============================================================================↵
    -0.06
     قدر
    -0.06
     NullPointerException
    -0.06
    POSITIVE LOGITS
     thyroid
    0.07
     pickup
    0.07
    /tools
    0.06
    /end
    0.06
     fitting
    0.06
     ait
    0.06
    exter
    0.06
     Hind
    0.06
     stitching
    0.06
    _hold
    0.06
    Act Density 0.000%

    No Known Activations