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

    Neuronpedia

    INDEX
    Explanations

    Cavanaugh

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     CRUD
    -0.07
     постоянно
    -0.07
     theft
    -0.07
     Mouth
    -0.06
     onslaught
    -0.06
     سب
    -0.06
     그래서
    -0.06
    因此
    -0.06
     manned
    -0.06
     Boiler
    -0.06
    POSITIVE LOGITS
    AE
    0.07
    inal
    0.07
    IALIZ
    0.06
     Chavez
    0.06
    也
    0.06
    INAL
    0.06
    PERT
    0.06
    tual
    0.06
     davranış
    0.06
    acellular
    0.06
    Act Density 0.004%

    No Known Activations