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

    Neuronpedia

    INDEX
    Explanations

    Special characters and "this"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .OrderBy
    -0.06
    _qs
    -0.06
     scrutiny
    -0.06
     patrol
    -0.06
    یم
    -0.06
     яй
    -0.06
     Arrow
    -0.06
     Lever
    -0.06
     blending
    -0.06
    AMB
    -0.06
    POSITIVE LOGITS
    =models
    0.07
    Λ
    0.07
    χω
    0.06
     biased
    0.06
    makt
    0.06
     pháp
    0.06
    390
    0.06
    _THE
    0.06
     dun
    0.06
    Bulletin
    0.06
    Act Density 0.015%

    No Known Activations