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

    Neuronpedia

    INDEX
    Explanations

    if

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    >NN
    -0.06
     notoriously
    -0.06
    MOVE
    -0.06
     Bedford
    -0.06
    _Manager
    -0.06
     aumento
    -0.06
    ithmetic
    -0.06
     sunny
    -0.06
    og
    -0.06
    275
    -0.06
    POSITIVE LOGITS
     flock
    0.07
    弾
    0.07
     若要
    0.07
     Freel
    0.06
    .How
    0.06
    ีฬ
    0.06
     designers
    0.06
     크
    0.06
    Authors
    0.06
     Anast
    0.06
    Act Density 0.016%

    No Known Activations