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

    Neuronpedia

    INDEX
    Explanations

    code and data structures

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     перег
    -0.08
    :hidden
    -0.07
     unins
    -0.06
     галуз
    -0.06
    -ro
    -0.06
    (Context
    -0.06
    _bounds
    -0.06
    $form
    -0.06
     GF
    -0.06
    lol
    -0.06
    POSITIVE LOGITS
     tossing
    0.07
     reviewer
    0.06
     localhost
    0.06
    	↵	↵
    0.06
    IFIC
    0.06
    iar
    0.06
     رفع
    0.06
    uye
    0.06
    яж
    0.06
     multiplier
    0.06
    Act Density 0.007%

    No Known Activations