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

    Neuronpedia

    INDEX
    Explanations

    whims

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    סרט
    -0.08
    }')↵
    -0.07
     endorsements
    -0.07
    armor
    -0.07
    video
    -0.07
    FTP
    -0.07
    辅导
    -0.07
     alerted
    -0.07
    _testing
    -0.07
    ㎜
    -0.07
    POSITIVE LOGITS
    กระบวน
    0.08
    Credentials
    0.08
    党风廉政
    0.07
    שמחה
    0.07
    ปกครอง
    0.07
     Churchill
    0.07
    蝉
    0.07
     UILabel
    0.07
    Reg
    0.07
     Zac
    0.07
    Act Density 0.002%

    No Known Activations