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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cestu
    -0.06
    �
    -0.06
    _escape
    -0.06
    _deinit
    -0.06
     přece
    -0.06
    ροι
    -0.06
    YTE
    -0.06
    bian
    -0.06
     cupid
    -0.06
     mort
    -0.06
    POSITIVE LOGITS
    justify
    0.07
    ]/
    0.07
    .'↵↵
    0.07
     
↵ 
↵
    0.07
    "));
↵
    0.06
     LOCATION
    0.06
     Conditions
    0.06
     in
    0.06
     aiding
    0.06
     Komment
    0.06
    Act Density 0.001%

    No Known Activations