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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Provision
    -0.09
     nutshell
    -0.08
     provision
    -0.08
     tine
    -0.07
     Anth
    -0.07
     surat
    -0.07
     IRA
    -0.07
     धो
    -0.07
    ativity
    -0.07
    uhake
    -0.07
    POSITIVE LOGITS
     origen
    0.08
    ാടി
    0.08
    ாள்
    0.08
    -origin
    0.07
     amacı
    0.07
     પુ
    0.07
     reve
    0.07
     направ
    0.07
     касается
    0.07
    Origen
    0.07
    Act Density 0.011%

    No Known Activations