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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vapor
    -0.07
     SOUND
    -0.07
     fool
    -0.07
    ventory
    -0.06
     корпус
    -0.06
    REA
    -0.06
     OSS
    -0.06
     транс
    -0.06
    へと
    -0.06
     Thế
    -0.06
    POSITIVE LOGITS
     dishonest
    0.07
    .expr
    0.07
    \",\"
    0.06
    -Headers
    0.06
    unched
    0.06
    fadeIn
    0.06
    Financial
    0.06
    uters
    0.06
    __("
    0.06
     EM
    0.06
    Act Density 0.000%

    No Known Activations