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

    Neuronpedia

    INDEX
    Explanations

    down

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _tE
    -0.07
     zp
    -0.06
    edo
    -0.06
     трохи
    -0.06
    oto
    -0.06
    ẫ
    -0.06
    nger
    -0.06
     jap
    -0.06
    恩
    -0.05
     predic
    -0.05
    POSITIVE LOGITS
    URLOPT
    0.07
     holds
    0.06
     мі
    0.06
    Inside
    0.06
     dém
    0.06
     compounded
    0.06
     refine
    0.06
     anatomy
    0.06
    otherapy
    0.06
     ANY
    0.06
    Act Density 0.003%

    No Known Activations