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

    Neuronpedia

    INDEX
    Explanations

    informed and protected

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     деца
    0.47
     TRIAL
    0.44
     물
    0.42
    Rotation
    0.41
     కారణంగా
    0.41
     плохо
    0.41
    ahirkan
    0.41
    illation
    0.40
    建築
    0.40
    LETIN
    0.39
    POSITIVE LOGITS
    gger
    0.48
     perny
    0.46
    celikle
    0.45
    ercus
    0.45
     envolv
    0.44
     granular
    0.44
    gü
    0.44
     subjet
    0.44
     turno
    0.43
     vestido
    0.42
    Act Density 0.004%

    No Known Activations