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

    Neuronpedia

    INDEX
    Explanations

    is and are

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Concern
    -0.06
     rogue
    -0.06
     rolls
    -0.06
    _validator
    -0.06
     roll
    -0.06
    _magic
    -0.06
    ng
    -0.06
    -legged
    -0.06
     inventions
    -0.06
    .chk
    -0.05
    POSITIVE LOGITS
     SEA
    0.07
    XYZ
    0.07
    /sn
    0.06
     民
    0.06
     RCMP
    0.06
     Định
    0.06
    abase
    0.06
    omu
    0.06
    touches
    0.06
    mouseleave
    0.06
    Act Density 0.144%

    No Known Activations