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

    Neuronpedia

    INDEX
    Explanations

    likely

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    prt
    -0.08
    _ra
    -0.08
    ’an
    -0.07
     trai
    -0.07
     perfection
    -0.07
    'an
    -0.07
     //--------------------------------
    -0.07
    ाओ
    -0.07
     gave
    -0.07
     JPanel
    -0.07
    POSITIVE LOGITS
     likely
    0.14
    likely
    0.10
     unlikely
    0.09
     Likely
    0.09
     limp
    0.08
    flight
    0.07
     likelihood
    0.07
     probability
    0.07
    _fact
    0.06
     clear
    0.06
    Act Density 0.018%

    No Known Activations