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

    Neuronpedia

    INDEX
    Explanations

    Worthiness

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fotos
    -0.07
     accompanies
    -0.07
    arias
    -0.07
     cuz
    -0.07
     parked
    -0.07
     שהיה
    -0.07
     anesthesia
    -0.07
     dez
    -0.07
     Kad
    -0.07
     Venezuela
    -0.07
    POSITIVE LOGITS
    쥡
    0.07
    .jackson
    0.07
    辽
    0.07
    🖑
    0.07
     REM
    0.06
    Flexible
    0.06
     param
    0.06
    -dot
    0.06
    	source
    0.06
    	Print
    0.06
    Act Density 0.024%

    No Known Activations