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

    Neuronpedia

    INDEX
    Explanations

    respond using

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ethyst
    0.57
    pet
    0.57
    elor
    0.55
    ovar
    0.53
    ptive
    0.52
    otin
    0.52
    igin
    0.51
    ed
    0.50
    beros
    0.49
    scaping
    0.49
    POSITIVE LOGITS
    ](../
    0.49
     dauer
    0.47
     الخارجية
    0.43
     leeftijd
    0.43
     ganze
    0.42
     körper
    0.41
     и
    0.41
     och
    0.40
    ዎች
    0.40
     અને
    0.40
    Act Density 0.001%

    No Known Activations