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

    Neuronpedia

    INDEX
    Explanations

    synth

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    fund
    -0.07
    Guy
    -0.07
     Male
    -0.07
    _TAB
    -0.07
    ᄊ
    -0.07
     Yay
    -0.06
    _regex
    -0.06
     Manny
    -0.06
    An
    -0.06
     Is
    -0.06
    POSITIVE LOGITS
    可根据
    0.08
    情况下
    0.07
     inertia
    0.07
    .wp
    0.07
    ilarity
    0.07
    晤
    0.07
     ileti
    0.07
    WATCH
    0.06
     mai
    0.06
     لكم
    0.06
    Act Density 0.001%

    No Known Activations