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

    Neuronpedia

    INDEX
    Explanations

    potential outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ро
    0.77
    ة
    0.75
    ру
    0.73
    с
    0.68
    ме
    0.66
    illä
    0.66
     I
    0.66
    art
    0.66
    лі
    0.65
    know
    0.64
    POSITIVE LOGITS
     suitors
    0.69
    Possible
    0.68
     możli
    0.66
     potenc
    0.66
     futuros
    0.66
    เจอ
    0.65
     possibles
    0.64
     futurs
    0.64
     poten
    0.64
     potentials
    0.63
    Act Density 0.100%

    No Known Activations