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

    Neuronpedia

    INDEX
    Explanations

    copying and modifying data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iagnostic
    -0.08
     fallu
    -0.08
     hely
    -0.07
     ranging
    -0.07
    .be
    -0.07
     بهترین
    -0.07
    _radio
    -0.07
    quiet
    -0.07
    isco
    -0.07
     quiet
    -0.07
    POSITIVE LOGITS
     Auswirkungen
    0.12
     beein
    0.11
     betroffen
    0.11
    影响
    0.11
     mõjut
    0.10
    _SHARE
    0.10
     unintended
    0.10
     invloed
    0.10
     تاث
    0.10
     SESSION
    0.10
    Act Density 0.005%

    No Known Activations