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

    Neuronpedia

    INDEX
    Explanations

    feeling good

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sons
    -0.07
     hip
    -0.07
    Uid
    -0.07
     franchise
    -0.07
     anz
    -0.06
     Nah
    -0.06
     dies
    -0.06
     Isabel
    -0.06
    父亲
    -0.06
    への
    -0.06
    POSITIVE LOGITS
     φω
    0.08
    balanced
    0.07
     Redistributions
    0.07
     ع
    0.07
    '");↵
    0.06
    DropDown
    0.06
    _CONTINUE
    0.06
    .Shape
    0.06
    digit
    0.06
     ********************************************************************************
    0.06
    Act Density 0.030%

    No Known Activations