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

    Neuronpedia

    INDEX
    Explanations

    information

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    跑
    -0.06
    \Helper
    -0.06
    �
    -0.06
     emulation
    -0.06
    нич
    -0.06
    ipp
    -0.06
    ahaha
    -0.06
    _COMPLETE
    -0.06
     losses
    -0.06
     particle
    -0.06
    POSITIVE LOGITS
    """↵↵↵
    0.06
    “,
    0.06
    Uno
    0.06
    `='$
    0.06
     Convention
    0.06
     incid
    0.06
    九
    0.06
    اسیون
    0.06
    ρώ
    0.06
    なくな
    0.06
    Act Density 0.038%

    No Known Activations