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

    Neuronpedia

    INDEX
    Explanations

    descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    名
    -0.07
    Tumblr
    -0.06
     Quân
    -0.06
    plits
    -0.06
     VK
    -0.06
    _POINTS
    -0.06
     Fight
    -0.06
     CPC
    -0.06
     dwar
    -0.06
    Beautiful
    -0.06
    POSITIVE LOGITS
     suốt
    0.07
    sty
    0.07
     intimidate
    0.06
     Parser
    0.06
    ξ
    0.06
    PR
    0.06
    794
    0.06
     headaches
    0.06
     instability
    0.06
     sqlalchemy
    0.06
    Act Density 0.104%

    No Known Activations