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

    Neuronpedia

    INDEX
    Explanations

    Ill

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _orient
    -0.07
     Columbia
    -0.07
     thuyết
    -0.07
     省
    -0.07
     seria
    -0.07
     Mặt
    -0.06
    arks
    -0.06
     πρα
    -0.06
    Disp
    -0.06
     　　 　
    -0.06
    POSITIVE LOGITS
    	label
    0.07
    CFG
    0.06
     ui
    0.06
     CharSet
    0.06
    ochond
    0.06
     rebound
    0.06
    chema
    0.06
    мот
    0.06
     �
    0.06
    0.06
    Act Density 0.000%

    No Known Activations