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

    Neuronpedia

    INDEX
    Explanations

    `large`, `fundamentally`, `cloud`, `common`, `lead`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    HideFlags
    0.40
     うん
    0.40
     OBJECTTYPE
    0.39
    OutputType
    0.39
     kadın
    0.39
    گی
    0.39
     Tong
    0.39
    うん
    0.39
     isTestSource
    0.38
     devlet
    0.38
    POSITIVE LOGITS
     silent
    0.41
     delay
    0.39
     calm
    0.38
    环境中
    0.38
     supervisor
    0.38
     amongst
    0.37
     among
    0.37
    יי
    0.37
     supervisors
    0.37
     behavioral
    0.37
    Act Density 0.000%

    No Known Activations