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

    Neuronpedia

    INDEX
    Explanations

    which

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Chim
    -0.07
     diminish
    -0.06
     gut
    -0.06
    erot
    -0.06
    iffin
    -0.06
     Prevent
    -0.06
     attent
    -0.06
    LV
    -0.06
     Npgsql
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    	elsif
    0.07
    loy
    0.07
    .AutoScale
    0.06
    ?}",
    0.06
                ↵↵
    0.06
     principals
    0.06
    UTERS
    0.06
     atheists
    0.06
    ，再
    0.06
     而
    0.06
    Act Density 0.001%

    No Known Activations