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

    Neuronpedia

    INDEX
    Explanations

    team

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dab
    -0.07
    DEFAULT
    -0.07
     DevComponents
    -0.06
     Verb
    -0.06
    .IsMatch
    -0.06
    �
    -0.06
     beden
    -0.06
    \a
    -0.06
     trab
    -0.06
    日の
    -0.06
    POSITIVE LOGITS
    irmware
    0.06
    ISBN
    0.06
    acer
    0.06
     manipulating
    0.06
    Bid
    0.06
     Dice
    0.06
    forall
    0.06
    itra
    0.06
     labeling
    0.06
     excav
    0.06
    Act Density 0.000%

    No Known Activations