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

    Neuronpedia

    INDEX
    Explanations

    sensitive

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     대한
    -0.06
     prefs
    -0.06
     Parl
    -0.05
    \'
    -0.05
    	err
    -0.05
    enabled
    -0.05
    糖
    -0.05
    ucci
    -0.05
    berries
    -0.05
    .bc
    -0.05
    POSITIVE LOGITS
    .dirname
    0.07
    ?)↵↵
    0.07
    

↵
    0.06
    (Console
    0.06
    .tf
    0.06
     chatte
    0.06
    _IMETHOD
    0.06
     اش
    0.06
     deliberately
    0.06
    東
    0.06
    Act Density 0.413%

    No Known Activations