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

    Neuronpedia

    INDEX
    Explanations

    .org

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bit
    -0.08
     fascist
    -0.08
    .OPEN
    -0.07
    了大量的
    -0.07
     visceral
    -0.07
    봽
    -0.07
     люди
    -0.07
     с
    -0.07
     quoting
    -0.06
     cite
    -0.06
    POSITIVE LOGITS
    _inode
    0.08
    佰
    0.08
    *log
    0.08
    百强
    0.07
    🇴
    0.07
    ᴠ
    0.07
    Occup
    0.07
     MMI
    0.07
    /part
    0.07
    �
    0.07
    Act Density 0.002%

    No Known Activations