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

    Neuronpedia

    INDEX
    Explanations

    com

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -Sah
    -0.07
     реги
    -0.06
    alley
    -0.06
    .But
    -0.06
    ,[
    -0.06
     lượt
    -0.06
     Zust
    -0.06
    ALLE
    -0.06
    Tour
    -0.06
     kå
    -0.06
    POSITIVE LOGITS
    寸
    0.07
     finish
    0.07
    imed
    0.07
     goodness
    0.06
     Coal
    0.06
            
↵        
↵
    0.06
    overe
    0.06
     frm
    0.06
    н
    0.06
    -based
    0.06
    Act Density 0.010%

    No Known Activations