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

    Neuronpedia

    INDEX
    Explanations

    code/URLs/file paths

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     recurs
    -0.07
    .Track
    -0.07
     MATERIAL
    -0.07
     World
    -0.06
     فقط
    -0.06
     diren
    -0.06
    ynamics
    -0.06
    _RULE
    -0.06
    iв
    -0.06
    複
    -0.06
    POSITIVE LOGITS
    forcements
    0.06
    loud
    0.06
     piel
    0.06
     плод
    0.06
    pciones
    0.05
     potency
    0.05
    lığını
    0.05
     Herz
    0.05
     lawful
    0.05
     heavenly
    0.05
    Act Density 0.000%

    No Known Activations