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

    Neuronpedia

    INDEX
    Explanations

    code/technical text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fing
    -0.06
    .hd
    -0.06
     Hearts
    -0.06
    "Oh
    -0.06
    edla
    -0.06
     infected
    -0.06
    ”。
    -0.06
     Stop
    -0.06
    。
    -0.06
     dầu
    -0.06
    POSITIVE LOGITS
     subnet
    0.07
     действ
    0.07
    ﻟ�
    0.07
    	texture
    0.06
     мот
    0.06
    WHITE
    0.06
    ्ण
    0.06
     creatively
    0.06
    QUAL
    0.06
    grupo
    0.06
    Act Density 0.000%

    No Known Activations