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

    Neuronpedia

    INDEX
    Explanations

    say "program"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _frm
    -0.08
     şirket
    -0.07
    Alchemy
    -0.07
     grasp
    -0.07
    ixel
    -0.07
     그것을
    -0.07
     hairst
    -0.06
     same
    -0.06
     tt
    -0.06
    issing
    -0.06
    POSITIVE LOGITS
     vec
    0.07
    伊利
    0.06
    ап
    0.06
    .substring
    0.06
    _ru
    0.06
     collections
    0.06
    代理人
    0.06
    vertis
    0.06
     Tun
    0.06
     revis
    0.06
    Act Density 0.015%

    No Known Activations