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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Free
    -0.07
    Fu
    -0.07
    φι
    -0.07
     업
    -0.07
     спос
    -0.06
     могла
    -0.06
    opo
    -0.06
    _IMP
    -0.06
     смог
    -0.06
     pois
    -0.06
    POSITIVE LOGITS
    Phrase
    0.08
    Latch
    0.07
     Stokes
    0.07
    krát
    0.06
    Select
    0.06
     Kč
    0.06
    DataRow
    0.06
    Interested
    0.06
    子の
    0.06
     UIG
    0.06
    Act Density 0.005%

    No Known Activations