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

    Neuronpedia

    INDEX
    Explanations

    what do you think about

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    0.23
    E
    0.21
    ες
    0.20
    fers
    0.18
     effet
    0.18
    L
    0.18
     Increased
    0.18
    S
    0.18
    0.18
    Lo
    0.18
    POSITIVE LOGITS
     what
    0.28
     why
    0.27
     bagaimana
    0.26
     him
    0.26
     cómo
    0.26
     hvad
    0.24
     kenapa
    0.24
     forskj
    0.24
     hvordan
    0.24
     whereabouts
    0.24
    Act Density 0.043%

    No Known Activations