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

    Neuronpedia

    INDEX
    Explanations

    run

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     состоит
    -0.07
    -manager
    -0.06
    .—
    -0.06
    通常
    -0.06
     Dayton
    -0.06
     ediyor
    -0.06
     beni
    -0.06
     Açık
    -0.06
     araştırma
    -0.06
     interviews
    -0.06
    POSITIVE LOGITS
    Peripheral
    0.07
    ného
    0.07
    �
    0.06
    isd
    0.06
    ній
    0.06
     equipments
    0.06
     Colomb
    0.06
    agic
    0.06
     şark
    0.06
    missions
    0.06
    Act Density 0.002%

    No Known Activations