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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Assets
    -0.07
     cham
    -0.06
    sales
    -0.06
    MIT
    -0.06
     away
    -0.06
    �
    -0.06
    esh
    -0.06
     státy
    -0.06
    _Z
    -0.06
    _BLEND
    -0.06
    POSITIVE LOGITS
    кових
    0.07
     начинает
    0.07
     assist
    0.07
    nee
    0.07
    έ
    0.06
     Eff
    0.06
    otron
    0.06
    Performed
    0.06
     فإن
    0.06
    Eff
    0.06
    Act Density 0.018%

    No Known Activations