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

    Neuronpedia

    INDEX
    Explanations

    formatted text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     зменш
    -0.07
    AJOR
    -0.06
     bồi
    -0.06
     TKey
    -0.06
    ičky
    -0.06
    ](↵
    -0.06
    .SharedPreferences
    -0.06
    십시오
    -0.06
     민
    -0.06
     стратег
    -0.06
    POSITIVE LOGITS
     nag
    0.07
    yled
    0.07
     also
    0.06
    　　　　　　　　　　　
    0.06
    .Find
    0.06
    wright
    0.06
     negligent
    0.06
    ,V
    0.06
    ct
    0.06
    oko
    0.06
    Act Density 0.026%

    No Known Activations