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

    Neuronpedia

    INDEX
    Explanations

    (disposing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    া�
    -0.07
    _cor
    -0.06
    dělen
    -0.06
     uphill
    -0.06
     comple
    -0.06
     opat
    -0.06
    _preview
    -0.06
    .menu
    -0.06
     roz
    -0.06
    compat
    -0.06
    POSITIVE LOGITS
     دام
    0.07
    竟
    0.07
    lio
    0.07
    Additional
    0.07
    Considering
    0.07
    Dream
    0.06
    UGHT
    0.06
     '')
    0.06
    Classes
    0.06
    ?;↵
    0.06
    Act Density 0.000%

    No Known Activations