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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tip
    -0.08
    .Console
    -0.07
     Fair
    -0.07
    ="+
    -0.07
     CCD
    -0.06
     consumes
    -0.06
     �
    -0.06
    ached
    -0.06
     konusu
    -0.06
    (op
    -0.06
    POSITIVE LOGITS
    _);↵
    0.08
     şiş
    0.06
     monkey
    0.06
    tero
    0.06
    hetto
    0.06
     ]]↵
    0.06
    ()");↵
    0.06
    yellow
    0.06
    _elt
    0.06
     emphasizing
    0.06
    Act Density 0.000%

    No Known Activations