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

    Neuronpedia

    INDEX
    Explanations

    OU

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Delay
    -0.07
     Sev
    -0.07
     [{↵
    -0.06
    icrobial
    -0.06
     aluminum
    -0.06
    ')])↵
    -0.06
     POD
    -0.06
     Lara
    -0.06
    matching
    -0.06
     incremented
    -0.06
    POSITIVE LOGITS
     trained
    0.07
     rupture
    0.07
     readline
    0.07
    499
    0.06
    không
    0.06
     jsem
    0.06
    /game
    0.06
     entertained
    0.06
     assigning
    0.06
     dem
    0.06
    Act Density 0.003%

    No Known Activations