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

    Neuronpedia

    INDEX
    Explanations

    ground

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Carmen
    -0.07
     niece
    -0.06
    盒
    -0.06
    公開
    -0.06
    mol
    -0.06
    collision
    -0.06
     pokus
    -0.06
     eagerly
    -0.06
    把
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     neden
    0.06
    ी.
    0.06
     gfx
    0.06
     distress
    0.06
     Religion
    0.06
     Adding
    0.06
    ъ
    0.06
    .restart
    0.06
     Kim
    0.06
     residents
    0.06
    Act Density 0.019%

    No Known Activations