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

    Neuronpedia

    INDEX
    Explanations

    A

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bình
    -0.07
     svém
    -0.07
     stress
    -0.07
     그것
    -0.06
    _boundary
    -0.06
     letz
    -0.06
    Secondary
    -0.06
    ับการ
    -0.06
     Olson
    -0.06
    —in
    -0.06
    POSITIVE LOGITS
     Analyst
    0.07
     anak
    0.06
    ']?>
    0.06
     Secondly
    0.06
    ké
    0.06
     coerce
    0.06
     Maharashtra
    0.05
    егра
    0.05
    ">',
    0.05
     �
    0.05
    Act Density 0.081%

    No Known Activations