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

    Neuronpedia

    INDEX
    Explanations

    up

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    `
    -0.07
    sys
    -0.07
     horrible
    -0.07
     lame
    -0.07
     Grande
    -0.07
    "
    -0.06
    77
    -0.06
     Film
    -0.06
    band
    -0.06
     Scotland
    -0.06
    POSITIVE LOGITS
     Sob
    0.07
     Cooling
    0.06
    ODULE
    0.06
     lot
    0.06
    .ViewModels
    0.06
     význam
    0.06
    _formatter
    0.06
    _ASYNC
    0.06
     cooling
    0.06
     Lis
    0.06
    Act Density 0.022%

    No Known Activations