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

    Neuronpedia

    INDEX
    Explanations

    whiplash

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Semana
    -0.09
    委员会
    -0.08
     édit
    -0.08
     Council
    -0.08
     ആരംഭ
    -0.08
     scheduling
    -0.08
     конферен
    -0.07
    筑
    -0.07
    വി�
    -0.07
    Lazy
    -0.07
    POSITIVE LOGITS
     हिं
    0.10
     violently
    0.10
     अचानक
    0.09
     traumatic
    0.09
     exert
    0.08
    -force
    0.08
    猛烈
    0.08
     violence
    0.08
     punish
    0.08
     violent
    0.08
    Act Density 0.006%

    No Known Activations