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
    (sizeof
    -0.07
    	un
    -0.06
     pues
    -0.06
    -qu
    -0.06
    :^(
    -0.06
     usado
    -0.06
    ...'
    -0.06
     comun
    -0.06
     assaulted
    -0.06
    -css
    -0.06
    POSITIVE LOGITS
     dominate
    0.08
     halinde
    0.07
    赏
    0.07
     protect
    0.07
     DHS
    0.07
    امت
    0.06
     ус
    0.06
     antenna
    0.06
     plug
    0.06
     Compilation
    0.06
    Act Density 0.001%

    No Known Activations