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

    Neuronpedia

    INDEX
    Explanations

    icle

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    $f
    -0.07
     ""
    -0.06
     Adolf
    -0.06
    lamaya
    -0.06
     business
    -0.06
    .gender
    -0.06
     narrower
    -0.06
    	break
    -0.06
    layın
    -0.06
    undefined
    -0.06
    POSITIVE LOGITS
    icle
    0.12
    icles
    0.11
    ickle
    0.09
    acle
    0.09
    ul
    0.08
    ittle
    0.08
    inkle
    0.08
    ull
    0.08
    uke
    0.07
    ile
    0.07
    Act Density 0.004%

    No Known Activations