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

    Neuronpedia

    INDEX
    Explanations

    code/technical language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     infinit
    -0.07
    partial
    -0.06
     intense
    -0.06
    _anchor
    -0.06
     düğ
    -0.06
    award
    -0.06
     bathtub
    -0.06
     lashes
    -0.06
    _wheel
    -0.06
     Releases
    -0.06
    POSITIVE LOGITS
    .Stop
    0.07
    Peer
    0.07
     함께
    0.07
     وفق
    0.06
     اینکه
    0.06
     ersten
    0.06
    imde
    0.06
     ';
↵
    0.06
     ได
    0.06
     semua
    0.06
    Act Density 0.000%

    No Known Activations