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

    Neuronpedia

    INDEX
    Explanations

    ized

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .easy
    -0.07
     Midnight
    -0.07
     valued
    -0.07
    -debug
    -0.06
     Vine
    -0.06
     Vin
    -0.06
    458
    -0.06
    dum
    -0.06
    dash
    -0.06
     saving
    -0.06
    POSITIVE LOGITS
     personalized
    0.07
    โรง
    0.07
    enght
    0.07
    .started
    0.06
     dejar
    0.06
    只要
    0.06
    ườ
    0.06
    .capitalize
    0.06
     Sunderland
    0.06
     đổ
    0.06
    Act Density 0.006%

    No Known Activations