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

    Neuronpedia

    INDEX
    Explanations

    code/data snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    acích
    -0.08
     crib
    -0.07
     corrupted
    -0.07
     CHE
    -0.07
     submar
    -0.06
    _inp
    -0.06
    續
    -0.06
    笑
    -0.06
    _man
    -0.06
    ioc
    -0.06
    POSITIVE LOGITS
     Jenna
    0.07
    	Int
    0.07
     Toolkit
    0.06
    .fa
    0.06
     znaj
    0.06
    letes
    0.06
    ogen
    0.06
    Inline
    0.06
    _val
    0.06
    ская
    0.06
    Act Density 0.000%

    No Known Activations