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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     WS
    -0.07
    xF
    -0.07
    iped
    -0.07
     AL
    -0.06
    ikh
    -0.06
    bots
    -0.06
    idel
    -0.06
     summers
    -0.06
     Yep
    -0.06
     careful
    -0.06
    POSITIVE LOGITS
    되었습니다
    0.07
     труд
    0.07
     enjo
    0.07
    atego
    0.06
     -->
↵
    0.06
    사무
    0.06
    경제
    0.06
    сь
    0.06
    \Carbon
    0.06
     sai
    0.06
    Act Density 0.072%

    No Known Activations