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

    Neuronpedia

    INDEX
    Explanations

    Daniels

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    part
    -0.07
     promoted
    -0.07
    .rooms
    -0.07
    Right
    -0.07
    ception
    -0.06
     inception
    -0.06
     Though
    -0.06
    STATE
    -0.06
     defendants
    -0.06
     Hindi
    -0.06
    POSITIVE LOGITS
    (WIN
    0.07
     �
    0.06
    (context
    0.06
     zvyš
    0.06
     serviceName
    0.06
     Sequ
    0.06
     жид
    0.06
    {o
    0.06
     projectId
    0.06
    .foo
    0.06
    Act Density 0.002%

    No Known Activations