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

    Neuronpedia

    INDEX
    Explanations

    actions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vids
    -0.07
    	me
    -0.07
     avere
    -0.06
     Victim
    -0.06
     Ignore
    -0.06
    朝着
    -0.06
     kicker
    -0.06
    祯
    -0.06
     cuz
    -0.06
     creepy
    -0.06
    POSITIVE LOGITS
     countries
    0.08
    ألم
    0.08
    STR
    0.07
     English
    0.07
    熟
    0.07
    卸
    0.07
    Nevertheless
    0.07
    等部门
    0.07
     CMS
    0.07
     Charl
    0.07
    Act Density 0.101%

    No Known Activations