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

    Neuronpedia

    INDEX
    Explanations

    ata

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    功夫
    -0.07
    倭
    -0.07
    擅自
    -0.07
    estruct
    -0.07
    	boost
    -0.07
    plier
    -0.06
     cancelButton
    -0.06
     reimbursement
    -0.06
    降幅
    -0.06
    /'.$
    -0.06
    POSITIVE LOGITS
     na
    0.07
    �
    0.07
     испыта
    0.07
    诞
    0.07
     Sabha
    0.06
    年第
    0.06
    �
    0.06
     самым
    0.06
    통신
    0.06
     homophobic
    0.06
    Act Density 0.000%

    No Known Activations