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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     desperately
    -0.07
     FORWARD
    -0.07
    Writer
    -0.07
    taient
    -0.06
    ritten
    -0.06
    Manager
    -0.06
    _Per
    -0.06
    ίζει
    -0.06
    oral
    -0.06
     varias
    -0.06
    POSITIVE LOGITS
     얼마
    0.07
    ิท
    0.07
     nymph
    0.06
     autoload
    0.06
     आक
    0.06
    !".
    0.06
     scarf
    0.06
    ाइ
    0.06
    	filename
    0.06
     EU
    0.06
    Act Density 0.109%

    No Known Activations