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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ("~/
    -0.08
     حر
    -0.07
     shootings
    -0.07
    .Make
    -0.07
     '">'
    -0.07
     Hab
    -0.06
    183
    -0.06
     distinctly
    -0.06
     swagger
    -0.06
     contraseña
    -0.06
    POSITIVE LOGITS
    lords
    0.07
     applies
    0.07
     rozum
    0.06
    angler
    0.06
    */)↵
    0.06
    	style
    0.06
    否
    0.06
     lick
    0.06
    ateur
    0.06
    amazon
    0.06
    Act Density 0.000%

    No Known Activations