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

    Neuronpedia

    INDEX
    Explanations

    code/programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ↵
    -0.07
     ту
    -0.06
     comparator
    -0.06
    	sig
    -0.06
     CCP
    -0.06
    倍
    -0.06
    =log
    -0.06
    ком
    -0.06
    CADE
    -0.06
     комп
    -0.06
    POSITIVE LOGITS
    /control
    0.07
    fix
    0.06
    edral
    0.06
     liberalism
    0.06
    _journal
    0.06
    plat
    0.06
    ecret
    0.06
    awesome
    0.05
    PE
    0.05
    (make
    0.05
    Act Density 0.132%

    No Known Activations