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

    Neuronpedia

    INDEX
    Explanations

    genetic mutations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Nu
    -0.07
     अब
    -0.07
     ramen
    -0.07
    ::{
    -0.07
    stride
    -0.07
     divine
    -0.06
     curled
    -0.06
     consensus
    -0.06
    izontally
    -0.06
    processed
    -0.06
    POSITIVE LOGITS
    andin
    0.06
    rick
    0.06
     �
    0.06
     oyuncu
    0.06
     лок
    0.06
     omin
    0.06
     又
    0.06
    ुछ
    0.06
    澤
    0.06
    μερ
    0.06
    Act Density 0.015%

    No Known Activations