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

    Neuronpedia

    INDEX
    Explanations

    varied text / code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ="
    -0.07
    바이
    -0.07
    选
    -0.06
    λιο
    -0.06
    =value
    -0.06
     Computational
    -0.06
     sourced
    -0.06
    _Exception
    -0.06
    	step
    -0.06
    ¬
    -0.06
    POSITIVE LOGITS
    ABILITY
    0.07
     pys
    0.07
     Crab
    0.07
     Rouge
    0.06
    북도
    0.06
     leakage
    0.06
    _probs
    0.06
     WI
    0.06
     искус
    0.06
    ',

↵
    0.06
    Act Density 0.000%

    No Known Activations