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

    Neuronpedia

    INDEX
    Explanations

    doing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _CENTER
    -0.07
    [o
    -0.07
    tons
    -0.06
    options
    -0.06
    -M
    -0.06
     z
    -0.06
    bro
    -0.06
    ы
    -0.06
    Div
    -0.06
    bl
    -0.06
    POSITIVE LOGITS
     Pulitzer
    0.07
     आश
    0.07
     �
    0.07
     evalu
    0.07
    IEW
    0.07
     semester
    0.06
     Prescott
    0.06
     donc
    0.06
    �
    0.06
     ActionType
    0.06
    Act Density 0.019%

    No Known Activations