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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    {}".
    -0.07
    heimer
    -0.06
    UserCode
    -0.06
    (src
    -0.06
    SW
    -0.06
    inciple
    -0.06
    xDA
    -0.06
    epad
    -0.06
    _isr
    -0.06
    qid
    -0.06
    POSITIVE LOGITS
    础
    0.07
     istiyorum
    0.07
     incon
    0.06
    цы
    0.06
     There
    0.06
    ß
    0.06
     justices
    0.06
     developmental
    0.06
     fasting
    0.06
     quand
    0.06
    Act Density 0.142%

    No Known Activations