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

    Neuronpedia

    INDEX
    Explanations

    administrate, organize, explain

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     MODIFY
    0.50
    FFIC
    0.49
    ADE
    0.49
    ELLE
    0.48
    UKA
    0.48
    </h2>
    0.48
     económicas
    0.46
     indicated
    0.45
     terb
    0.45
    AKER
    0.44
    POSITIVE LOGITS
    셨
    0.54
    spiele
    0.52
    ologisch
    0.49
    阂
    0.49
    睚
    0.48
    FlagSet
    0.48
    где
    0.47
    ಾಣ
    0.46
     игр
    0.46
    倜
    0.45
    Act Density 0.000%

    No Known Activations