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

    Neuronpedia

    INDEX
    Explanations

    hesse

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Regel
    -0.07
     trib
    -0.07
    <!--↵
    -0.07
    :";↵
    -0.07
    نع
    -0.06
    ยก
    -0.06
    .sav
    -0.06
    _iterator
    -0.06
    		↵		↵		↵
    -0.06
    -м
    -0.06
    POSITIVE LOGITS
     tess
    0.06
     leads
    0.06
     rifles
    0.06
     Stuttgart
    0.06
     physique
    0.06
     induce
    0.06
    .getMinutes
    0.06
    (connect
    0.06
    avage
    0.06
     grants
    0.06
    Act Density 0.240%

    No Known Activations