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

    Neuronpedia

    INDEX
    Explanations

    fat

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Manus
    -0.08
    _WEIGHT
    -0.07
    trzym
    -0.07
     rhyth
    -0.07
    痞
    -0.07
    有不少
    -0.07
    larınd
    -0.07
     cham
    -0.07
    _hostname
    -0.07
     craftsm
    -0.07
    POSITIVE LOGITS
     thinking
    0.08
     meeting
    0.07
    交谈
    0.07
    }}">↵
    0.07
    Haunted
    0.07
    StoryboardSegue
    0.07
    估算
    0.07
     death
    0.07
    Thinking
    0.06
    meeting
    0.06
    Act Density 0.004%

    No Known Activations