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

    Neuronpedia

    INDEX
    Explanations

    worth

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Psy
    -0.07
    /pp
    -0.06
     cháy
    -0.06
    .TextField
    -0.06
    KeyUp
    -0.06
    โร
    -0.06
     XSS
    -0.06
    icorn
    -0.06
     js
    -0.05
    .leave
    -0.05
    POSITIVE LOGITS
     Reliable
    0.07
    ौक
    0.07
     erotik
    0.06
    кість
    0.06
    .','
    0.06
    -long
    0.06
    Meanwhile
    0.06
    .env
    0.06
     railing
    0.06
    /react
    0.06
    Act Density 0.012%

    No Known Activations