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

    Neuronpedia

    INDEX
    Explanations

    question

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    обав
    -0.07
     سه
    -0.07
    maid
    -0.06
    (ChatColor
    -0.06
     κά
    -0.06
    izzie
    -0.06
    registro
    -0.06
     Tribute
    -0.05
    ология
    -0.05
    #Region
    -0.05
    POSITIVE LOGITS
     phenotype
    0.07
    }

↵
    0.06
     dominating
    0.06
     stays
    0.06
     romant
    0.06
    зь
    0.06
     splendid
    0.06
     zoom
    0.06
    ;↵
    0.06
    __);↵↵
    0.06
    Act Density 0.000%

    No Known Activations