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

    Neuronpedia

    INDEX
    Explanations

    i

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ensive
    -0.07
     recycl
    -0.07
    (dis
    -0.07
     billionaires
    -0.07
     فن
    -0.07
     Mol
    -0.06
     道
    -0.06
     uf
    -0.06
    _ph
    -0.06
    Ｍ
    -0.06
    POSITIVE LOGITS
     Jing
    0.07
    Percent
    0.07
     lettre
    0.07
    σετε
    0.06
     ChatColor
    0.06
    .Web
    0.06
     newly
    0.06
     dlou
    0.06
     uzman
    0.06
    	redirect
    0.06
    Act Density 0.010%

    No Known Activations