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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     MG
    -0.07
     ingresar
    -0.07
     LET
    -0.07
    张
    -0.07
    ベース
    -0.07
    _sel
    -0.07
    fers
    -0.07
     histórico
    -0.07
    (DEBUG
    -0.07
     faux
    -0.06
    POSITIVE LOGITS
    鬯
    0.08
    ension
    0.07
    _CONTROL
    0.07
    aisy
    0.07
    Friend
    0.07
    驯
    0.07
    ㎎
    0.07
    scp
    0.07
    dia
    0.07
    	connection
    0.07
    Act Density 0.001%

    No Known Activations