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

    Neuronpedia

    INDEX
    Explanations

    5

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     contends
    -0.07
    istry
    -0.07
     Citizens
    -0.07
    йтесь
    -0.07
     gently
    -0.07
    	Context
    -0.06
    متاب
    -0.06
     الرغم
    -0.06
    harma
    -0.06
     gracias
    -0.06
    POSITIVE LOGITS
     WCS
    0.07
     colon
    0.07
    촥
    0.07
    spacer
    0.07
    👽
    0.06
     בראש
    0.06
     canned
    0.06
    published
    0.06
    发布会上
    0.06
     Coy
    0.06
    Act Density 0.006%

    No Known Activations