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

    Neuronpedia

    INDEX
    Explanations

    Needles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    DOWN
    -0.06
    ��
    -0.06
     zim
    -0.06
     seemingly
    -0.06
    (previous
    -0.06
    what
    -0.06
     začátku
    -0.06
     interviews
    -0.06
    down
    -0.06
     appearing
    -0.06
    POSITIVE LOGITS
     dřev
    0.06
     evt
    0.06
     Βασ
    0.06
     würde
    0.06
    -demo
    0.06
     Swal
    0.06
    .El
    0.06
    CLLocation
    0.06
    ]int
    0.06
    ，同时
    0.06
    Act Density 0.046%

    No Known Activations