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

    Neuronpedia

    INDEX
    Explanations

    (x

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     خلف
    -0.07
     cbo
    -0.07
     preds
    -0.07
     сказ
    -0.06
     culpa
    -0.06
     jente
    -0.06
     guessing
    -0.06
    aan
    -0.06
     Rocket
    -0.06
     imposs
    -0.06
    POSITIVE LOGITS
    almö
    0.07
    cerer
    0.06
     pores
    0.06
     mutations
    0.06
    ById
    0.06
    uffix
    0.06
     собира
    0.06
    cob
    0.06
    Mahon
    0.06
    .random
    0.06
    Act Density 0.000%

    No Known Activations