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

    Neuronpedia

    INDEX
    Explanations

    code equality/inequality operators

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (KeyEvent
    -0.07
    !↵↵↵↵
    -0.07
    ()
↵
↵
↵
    -0.07
    erate
    -0.07
    ？”
    -0.06
    ?"↵↵↵↵
    -0.06
    memberOf
    -0.06
     (;
    -0.06
    )=='
    -0.06
    update
    -0.06
    POSITIVE LOGITS
    함
    0.06
     anti
    0.06
     rails
    0.06
     indications
    0.06
     vou
    0.06
    REG
    0.06
    icha
    0.06
    reg
    0.06
     reg
    0.06
    getStringExtra
    0.06
    Act Density 0.028%

    No Known Activations