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

    Neuronpedia

    INDEX
    Explanations

    math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bark
    -0.07
    іти
    -0.07
     nause
    -0.06
     Mc
    -0.06
     tarif
    -0.06
     naughty
    -0.06
    어서
    -0.06
     فار
    -0.06
     الأول
    -0.06
     flesh
    -0.06
    POSITIVE LOGITS
    .row
    0.06
    DMI
    0.06
    .setBackground
    0.06
     ignited
    0.06
    CG
    0.06
     genetic
    0.06
     khắc
    0.06
     effortlessly
    0.06
    Э
    0.06
    CTION
    0.06
    Act Density 0.001%

    No Known Activations