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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     poke
    -0.07
    Csv
    -0.07
     vests
    -0.07
    🎤
    -0.07
     famously
    -0.07
    UCCEEDED
    -0.07
    专访
    -0.06
    			
↵			
↵
    -0.06
    配上
    -0.06
     shorts
    -0.06
    POSITIVE LOGITS
    дал
    0.08
    벡
    0.07
     toolStrip
    0.06
     yönel
    0.06
    싫
    0.06
    между
    0.06
     серь
    0.06
    ര
    0.06
    𝓼
    0.06
    싯
    0.06
    Act Density 0.000%

    No Known Activations