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

    Neuronpedia

    INDEX
    Explanations

    Id

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    662
    -0.08
     arenas
    -0.07
     CW
    -0.07
    423
    -0.07
    445
    -0.07
    661
    -0.07
    663
    -0.07
    113
    -0.07
    613
    -0.07
    706
    -0.06
    POSITIVE LOGITS
     절
    0.07
     ah
    0.07
    цин
    0.06
    ImageSharp
    0.06
    ?",↵
    0.06
    pokemon
    0.06
     architectures
    0.06
    _RECE
    0.05
    そして
    0.05
    ullivan
    0.05
    Act Density 0.000%

    No Known Activations