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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pinpoint
    -0.06
    uren
    -0.06
    uft
    -0.06
    .nii
    -0.06
     Ziel
    -0.06
     Niet
    -0.06
     ně
    -0.06
    ielding
    -0.06
    มอ
    -0.06
    uerdo
    -0.06
    POSITIVE LOGITS
     redesign
    0.08
     interesting
    0.07
     прем
    0.06
    	r
    0.06
    ↵
↵
↵
    0.06
    yth
    0.06
    $↵↵
    0.06
     Handler
    0.06
    _allowed
    0.06
    ###↵↵
    0.06
    Act Density 0.012%

    No Known Activations