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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Equals
    -0.07
     aktu
    -0.07
    equal
    -0.07
    凌
    -0.06
    matching
    -0.06
    ضم
    -0.06
     tady
    -0.06
    .lazy
    -0.06
    Been
    -0.06
    IDGET
    -0.06
    POSITIVE LOGITS
    ;
    0.07
    olet
    0.07
    ibr
    0.07
    =search
    0.06
    olvimento
    0.06
    =date
    0.06
     Antarctic
    0.06
    (port
    0.06
    –
    0.06
     phys
    0.06
    Act Density 0.002%

    No Known Activations