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
    warm
    -0.06
     barbar
    -0.06
     deutschland
    -0.06
    _ins
    -0.06
     ______
    -0.06
     ла
    -0.06
    ibbean
    -0.06
     آل
    -0.06
    _prot
    -0.06
    poons
    -0.06
    POSITIVE LOGITS
    .require
    0.07
    -options
    0.06
    -elements
    0.06
    .tc
    0.06
    τής
    0.06
     PHI
    0.06
    \Customer
    0.06
     дев
    0.06
    ".↵↵↵↵
    0.06
     duel
    0.06
    Act Density 0.000%

    No Known Activations