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

    Neuronpedia

    INDEX
    Explanations

    worth

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ;%
    -0.07
    	canvas
    -0.06
    .token
    -0.06
     ReadOnly
    -0.06
    XHR
    -0.06
    .UTC
    -0.06
    (debug
    -0.06
    _duration
    -0.06
    Rare
    -0.06
    $",
    -0.06
    POSITIVE LOGITS
     convert
    0.06
     contention
    0.06
    となる
    0.06
     minha
    0.06
     �
    0.06
    business
    0.06
     strpos
    0.06
     wür
    0.06
     перей
    0.06
     claw
    0.06
    Act Density 0.126%

    No Known Activations