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

    Neuronpedia

    INDEX
    Explanations

    treatment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     minecraft
    -0.08
    _EXEC
    -0.07
     \""
    -0.06
    測
    -0.06
    he
    -0.06
    .AC
    -0.06
    _AD
    -0.06
    شتر
    -0.06
     theme
    -0.06
    .windows
    -0.06
    POSITIVE LOGITS
    ruptions
    0.07
    =&
    0.06
     intentionally
    0.06
    ızı
    0.06
    ={}↵
    0.06
     mindful
    0.06
     repr
    0.06
    plits
    0.06
    PRETTY
    0.06
    ||↵
    0.06
    Act Density 0.065%

    No Known Activations