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

    Neuronpedia

    INDEX
    Explanations

    Amazon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lish
    -0.32
    croll
    -0.28
     Pik
    -0.27
    atoi
    -0.26
     pin
    -0.26
     jot
    -0.26
    Centre
    -0.25
    oha
    -0.25
    orks
    -0.25
    lix
    -0.25
    POSITIVE LOGITS
    éĥģ
    0.30
    esch
    0.28
    ',['../
    0.28
    æłĸ
    0.28
    诲
    0.25
    款
    0.25
     Pres
    0.25
     Trim
    0.25
    ");//
    0.24
    åĪ·
    0.24
    Act Density 20.287%

    No Known Activations