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

    Neuronpedia

    INDEX
    Explanations

    Large numbers and comparisons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ARB
    -0.08
    QB
    -0.07
    arb
    -0.06
     NORMAL
    -0.06
    .Zip
    -0.06
     offered
    -0.06
    	offset
    -0.06
    instead
    -0.06
     stdClass
    -0.06
    esehen
    -0.06
    POSITIVE LOGITS
    {@
    0.07
     escre
    0.06
    ская
    0.06
     privileges
    0.06
     euch
    0.06
    ювання
    0.06
     FIRE
    0.06
     strands
    0.06
     полез
    0.06
     вертик
    0.06
    Act Density 0.018%

    No Known Activations