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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ras
    -0.07
    昃
    -0.07
     aras
    -0.07
    fl
    -0.07
    ți
    -0.07
    ant
    -0.07
    Ⱑ
    -0.07
     présent
    -0.06
    دافع
    -0.06
     apologize
    -0.06
    POSITIVE LOGITS
     valign
    0.07
    圻
    0.07
     cm
    0.07
     amalg
    0.07
     churches
    0.07
     shrink
    0.07
    moire
    0.07
    ulary
    0.07
    珂
    0.07
    Companies
    0.07
    Act Density 0.015%

    No Known Activations