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

    Neuronpedia

    INDEX
    Explanations

    -break

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     לראש
    -0.08
    |required
    -0.08
    <Sprite
    -0.07
    으
    -0.07
    seudo
    -0.07
    _third
    -0.07
     Pare
    -0.07
     coeff
    -0.07
    四十
    -0.07
    _comb
    -0.07
    POSITIVE LOGITS
     Rita
    0.07
    اور
    0.07
    esthesia
    0.07
     bags
    0.07
    手段
    0.07
     Sentinel
    0.07
    持續
    0.07
    @g
    0.07
    ỵ
    0.07
    _ER
    0.07
    Act Density 0.001%

    No Known Activations