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

    Neuronpedia

    INDEX
    Explanations

    Visible from a distance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wenig
    -0.07
     urinary
    -0.07
    浓缩
    -0.07
    micro
    -0.06
    OrUpdate
    -0.06
    ercial
    -0.06
    มากๆ
    -0.06
    북
    -0.06
     asia
    -0.06
    spa
    -0.06
    POSITIVE LOGITS
    'We
    0.07
    icted
    0.07
    �
    0.07
    _engine
    0.06
    饺子
    0.06
     Giov
    0.06
     ();
↵
    0.06
    Others
    0.06
     możliwość
    0.06
     rav
    0.06
    Act Density 0.037%

    No Known Activations