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

    Neuronpedia

    INDEX
    Explanations

    struct

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	height
    -0.07
    	bg
    -0.07
    ullo
    -0.06
    [B
    -0.06
    pike
    -0.06
    allow
    -0.06
    gg
    -0.06
     fork
    -0.06
    owing
    -0.06
    [file
    -0.06
    POSITIVE LOGITS
    탈
    0.07
    東京
    0.07
     MatButtonModule
    0.07
     NTN
    0.06
    なん
    0.06
    宽
    0.06
    ylül
    0.06
     downt
    0.06
     pneum
    0.06
     tatto
    0.06
    Act Density 0.001%

    No Known Activations