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

    Neuronpedia

    INDEX
    Explanations

    influence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     preempt
    -0.08
     Мет
    -0.06
     geek
    -0.06
    _BAR
    -0.06
    PCI
    -0.06
     Harden
    -0.06
     ｰ
    -0.06
     Fel
    -0.06
    .authorization
    -0.06
    RetVal
    -0.06
    POSITIVE LOGITS
     influence
    0.16
     Influence
    0.13
     influences
    0.12
     influencing
    0.09
     influential
    0.09
     influenced
    0.08
    fluence
    0.08
     контроль
    0.07
     вплив
    0.07
     analyst
    0.07
    Act Density 0.018%

    No Known Activations