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

    Neuronpedia

    INDEX
    Explanations

    ) =>

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Phil
    0.39
     ;-)
    0.39
    ʾ
    0.39
    yati
    0.38
    愘
    0.38
    โ
    0.38
    蜼
    0.38
    يدية
    0.37
     সময়ের
    0.36
     Phil
    0.36
    POSITIVE LOGITS
    na
    0.39
    atta
    0.39
    console
    0.38
     conso
    0.38
    aza
    0.37
    ques
    0.37
    va
    0.36
     flip
    0.36
                            
    0.35
     Example
    0.35
    Act Density 0.001%

    No Known Activations