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

    Neuronpedia

    INDEX
    Explanations

    plant leaves

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     quies
    0.49
     a
    0.47
     asesin
    0.47
    <0xA3>
    0.45
     dolores
    0.45
     liquefied
    0.44
     leaf
    0.44
     vínculos
    0.44
     olvid
    0.43
     pretext
    0.43
    POSITIVE LOGITS
    in
    0.64
    as
    0.57
    ll
    0.57
    v
    0.57
    h
    0.53
    an
    0.50
    im
    0.49
    ح
    0.49
    t
    0.48
    institut
    0.47
    Act Density 0.000%

    No Known Activations