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

    Neuronpedia

    INDEX
    Explanations

    magic number

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    N
    0.54
    U
    0.48
    K
    0.46
     dư
    0.44
     president
    0.41
    metrics
    0.41
    文
    0.41
    T
    0.41
     controlar
    0.41
    施工
    0.39
    POSITIVE LOGITS
    👳
    0.50
     একজনের
    0.50
     インド
    0.50
    لک
    0.49
    ☺
    0.49
    ）・
    0.48
    reys
    0.46
     丿
    0.46
     Considering
    0.46
     ವಿಶ್ವ
    0.46
    Act Density 0.000%

    No Known Activations