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

    Neuronpedia

    INDEX
    Explanations

    sub

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ớp
    -0.07
    jad
    -0.07
    銀行
    -0.06
     Ion
    -0.06
    IÓN
    -0.06
    鮮
    -0.06
     Orbit
    -0.06
    ocide
    -0.06
     ци
    -0.06
     activating
    -0.06
    POSITIVE LOGITS
    _upper
    0.06
    /pm
    0.06
     debated
    0.06
     châu
    0.06
    Pairs
    0.06
     succeeds
    0.06
    	cfg
    0.06
     wander
    0.06
    -da
    0.06
     freshness
    0.06
    Act Density 0.004%

    No Known Activations