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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Honor
    -0.07
    거래
    -0.07
    죄
    -0.06
     NOW
    -0.06
    ３
    -0.06
     skiing
    -0.06
    \API
    -0.06
    ฒ
    -0.06
    (news
    -0.06
     cs
    -0.06
    POSITIVE LOGITS
    visející
    0.07
     wchar
    0.06
    	Application
    0.06
    	UPROPERTY
    0.06
    ostringstream
    0.06
     strlen
    0.06
    EditMode
    0.06
    iqueta
    0.06
    oulder
    0.06
     Palestinian
    0.06
    Act Density 0.040%

    No Known Activations