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

    Neuronpedia

    INDEX
    Explanations

    guidance and indication

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    aph
    -0.08
     Laf
    -0.08
    ull
    -0.08
     jay
    -0.07
     rob
    -0.07
     emigr
    -0.07
     sahibi
    -0.07
    andler
    -0.07
     병
    -0.07
    adh
    -0.07
    POSITIVE LOGITS
     okvir
    0.12
     rather
    0.11
     vielmehr
    0.10
     лишь
    0.10
     lediglich
    0.10
     скорее
    0.10
     בלבד
    0.09
     illustrative
    0.09
    方便
    0.09
     tentative
    0.09
    Act Density 0.055%

    No Known Activations