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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Comedy
    -0.08
    .Contains
    -0.07
     spelling
    -0.07
     CVE
    -0.07
    ्तव
    -0.06
     brew
    -0.06
     BIOS
    -0.06
     Consum
    -0.06
     Mutable
    -0.06
     histor
    -0.06
    POSITIVE LOGITS
    _Index
    0.07
     Vak
    0.07
    (by
    0.06
     acquaint
    0.06
    ardin
    0.06
     args
    0.06
    Oh
    0.06
     injuring
    0.05
    :]↵
    0.05
     vak
    0.05
    Act Density 0.055%

    No Known Activations