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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Improved
    -0.06
    _OUT
    -0.06
    ۱۲
    -0.06
    Adding
    -0.06
    India
    -0.06
    atabase
    -0.06
    _movies
    -0.06
    _house
    -0.06
     delaying
    -0.06
    DIRECT
    -0.06
    POSITIVE LOGITS
    (errorMessage
    0.07
    <source
    0.07
    ッチ
    0.07
     FM
    0.07
    icks
    0.06
     fuse
    0.06
     فر
    0.06
    -Cds
    0.06
    GENER
    0.06
     tactic
    0.06
    Act Density 0.007%

    No Known Activations