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

    Neuronpedia

    INDEX
    Explanations

    codes or identifiers

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    もっと
    0.35
     پیدا
    0.34
    より
    0.33
    えず
    0.33
    ỡi
    0.32
    䛊
    0.31
     claramente
    0.31
    ÍC
    0.31
     basically
    0.31
     van
    0.30
    POSITIVE LOGITS
     Bhub
    0.41
     habilidad
    0.38
    strength
    0.38
    נים
    0.36
     কাল
    0.36
    तलब
    0.36
    Ⲗ
    0.35
    Strength
    0.35
    Boundary
    0.34
    subNav
    0.34
    Act Density 0.012%

    No Known Activations