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

    Neuronpedia

    INDEX
    Explanations

    name

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tolerate
    -0.07
    猊
    -0.07
    lient
    -0.06
    furt
    -0.06
    _Selection
    -0.06
    (find
    -0.06
    ’int
    -0.06
     belie
    -0.06
     garner
    -0.06
    uentes
    -0.06
    POSITIVE LOGITS
    _Se
    0.07
     opi
    0.07
    }.${
    0.07
     eps
    0.07
     resale
    0.07
     oci
    0.06
    ittal
    0.06
    Management
    0.06
     asm
    0.06
    _FINISH
    0.06
    Act Density 0.004%

    No Known Activations