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

    Neuronpedia

    INDEX
    Explanations

    Not working/broken

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pection
    -0.07
     beled
    -0.07
     yıllık
    -0.07
     abducted
    -0.06
     JB
    -0.06
    Increment
    -0.06
    gressor
    -0.06
    rtc
    -0.06
     pharmac
    -0.06
    products
    -0.06
    POSITIVE LOGITS
    ьв
    0.07
     Slovakia
    0.07
    _diag
    0.06
    .delegate
    0.06
     souls
    0.06
    aldi
    0.06
    eselect
    0.06
    ('\
    0.06
     CONVERT
    0.06
     conceptual
    0.06
    Act Density 0.056%

    No Known Activations