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

    Neuronpedia

    INDEX
    Explanations

    written language with symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.06
     expect
    -0.06
     Mob
    -0.06
     где
    -0.06
    /events
    -0.06
     airy
    -0.06
     المش
    -0.06
     Prov
    -0.06
    .Box
    -0.06
    VertexAttrib
    -0.06
    POSITIVE LOGITS
     flats
    0.06
    glm
    0.06
     полити
    0.06
    丹
    0.06
     Bless
    0.05
    л
    0.05
    !",↵
    0.05
     :=
    0.05
    .mock
    0.05
     бли
    0.05
    Act Density 0.000%

    No Known Activations