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

    Neuronpedia

    INDEX
    Explanations

    fieldset

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     اجرا
    -0.07
    oomla
    -0.07
     residue
    -0.07
     styling
    -0.07
     toxicity
    -0.07
    427
    -0.06
    頭
    -0.06
    	template
    -0.06
     present
    -0.06
    .algorithm
    -0.06
    POSITIVE LOGITS
     vyz
    0.07
    ELS
    0.06
    (gt
    0.06
     ej
    0.06
     ….
    0.06
     Cheers
    0.06
    -task
    0.06
     PATCH
    0.06
    />.
    0.06
    ып
    0.06
    Act Density 0.001%

    No Known Activations