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

    Neuronpedia

    INDEX
    Explanations

    Pika Labs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    atted
    0.42
     Rel
    0.39
    罕
    0.37
     ←
    0.37
    tilde
    0.37
    いたい
    0.37
    abetes
    0.36
    ütü
    0.36
    hamming
    0.36
     mathematical
    0.36
    POSITIVE LOGITS
    嫨
    0.41
    новение
    0.39
     Kear
    0.39
     గో
    0.36
    ização
    0.36
    Moh
    0.36
    ସ
    0.36
    zad
    0.35
    逪
    0.35
    alsey
    0.35
    Act Density 0.011%

    No Known Activations