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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Max
    -0.06
     muscle
    -0.06
    Na
    -0.06
    -terminal
    -0.06
     Australia
    -0.06
    _probability
    -0.06
     gastr
    -0.06
     fashionable
    -0.06
    _approved
    -0.06
    咲
    -0.06
    POSITIVE LOGITS
     бур
    0.08
    .pen
    0.07
     conforms
    0.07
    огу
    0.07
     �
    0.06
    manuel
    0.06
     mě
    0.06
     درجة
    0.06
     emerging
    0.06
     @
    0.06
    Act Density 0.012%

    No Known Activations