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

    Neuronpedia

    INDEX
    Explanations

    output

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	lbl
    -0.07
     понима
    -0.07
     花
    -0.06
    �
    -0.06
     рук
    -0.06
    .xz
    -0.06
     sudoku
    -0.06
    跟
    -0.06
    arLayout
    -0.06
     Lond
    -0.06
    POSITIVE LOGITS
     earnings
    0.07
     NFS
    0.07
    REMOTE
    0.07
    008
    0.07
    sil
    0.06
     Behind
    0.06
    auses
    0.06
     Multi
    0.06
    MLE
    0.06
    bilt
    0.06
    Act Density 0.027%

    No Known Activations