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

    Neuronpedia

    INDEX
    Explanations

    or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    amped
    -0.07
    -ins
    -0.07
    英雄
    -0.07
     kijken
    -0.06
     zf
    -0.06
     ARGS
    -0.06
    _ARROW
    -0.06
     EINVAL
    -0.06
    ُن
    -0.06
    }}">↵
    -0.06
    POSITIVE LOGITS
     Leg
    0.06
    /"+
    0.06
     excuse
    0.06
    thood
    0.06
     referrals
    0.06
    water
    0.06
     frag
    0.05
    emotion
    0.05
     الام
    0.05
     bölge
    0.05
    Act Density 0.030%

    No Known Activations