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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     strips
    -0.08
     Baker
    -0.08
    _subs
    -0.07
    (prev
    -0.07
    _sub
    -0.07
     VG
    -0.07
    inta
    -0.07
    vd
    -0.07
    ustum
    -0.07
    .getAddress
    -0.06
    POSITIVE LOGITS
    时间
    0.07
     это
    0.07
     Việc
    0.06
    ın
    0.06
     SQLITE
    0.06
     altri
    0.06
     PriorityQueue
    0.06
     שצריך
    0.06
     trouble
    0.06
     בשביל
    0.06
    Act Density 0.008%

    No Known Activations