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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Mag
    -0.07
    avec
    -0.07
    respond
    -0.07
    .sparse
    -0.06
    predict
    -0.06
    Rich
    -0.06
    Mana
    -0.06
    TF
    -0.06
    Cancelable
    -0.06
     EUR
    -0.06
    POSITIVE LOGITS
    chal
    0.06
    imens
    0.06
    ılıp
    0.06
     bringen
    0.06
     getting
    0.06
     onions
    0.06
     woods
    0.06
     Zhu
    0.06
    もり
    0.06
    çi
    0.06
    Act Density 0.032%

    No Known Activations