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

    Neuronpedia

    INDEX
    Explanations

    Code execution

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.07
     needles
    -0.07
     보여
    -0.07
     PJ
    -0.07
    gw
    -0.07
     گاه
    -0.07
     groundbreaking
    -0.06
    checksum
    -0.06
     회
    -0.06
    ()"
    -0.06
    POSITIVE LOGITS
    ilenames
    0.08
    _REST
    0.07
     А
    0.06
    utton
    0.06
    rotate
    0.06
     strict
    0.06
     triangles
    0.06
    ,arg
    0.06
    rgan
    0.05
     만
    0.05
    Act Density 0.003%

    No Known Activations