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

    Neuronpedia

    INDEX
    Explanations

    ERA

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wsz
    -0.07
     rumored
    -0.06
    CellStyle
    -0.06
    	freopen
    -0.06
     bip
    -0.06
     přip
    -0.06
     trao
    -0.06
    ------+
    -0.06
     sym
    -0.06
     事
    -0.05
    POSITIVE LOGITS
    示
    0.07
     onSuccess
    0.07
     studi
    0.07
    シュ
    0.06
     `,↵
    0.06
     rehabilit
    0.06
    #End
    0.06
    Separator
    0.06
     Ess
    0.06
     UA
    0.06
    Act Density 0.002%

    No Known Activations