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

    Neuronpedia

    INDEX
    Explanations

    phase

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ø£Ùħ
    -0.27
    ifecycle
    -0.26
    SetColor
    -0.25
     Speak
    -0.24
    宾客
    -0.24
     whereabouts
    -0.24
    éĿłçĿĢ
    -0.24
     Ops
    -0.23
    bru
    -0.23
    æ¯Ĺ
    -0.23
    POSITIVE LOGITS
    åħ¸åŀĭ
    0.27
    缴åįĩ
    0.26
    ig
    0.26
    èľķ
    0.26
    忽çķ¥
    0.25
    distinct
    0.25
    rail
    0.25
     farms
    0.25
     illustrated
    0.25
    igs
    0.24
    Act Density 0.576%

    No Known Activations