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

    Neuronpedia

    INDEX
    Explanations

    answer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _std
    -0.07
    ir
    -0.06
    .My
    -0.06
    "is
    -0.06
    相对于
    -0.06
     une
    -0.06
     realism
    -0.06
     (...)
    -0.06
     afs
    -0.06
     xu
    -0.06
    POSITIVE LOGITS
    בוע
    0.07
    BY
    0.07
     sofas
    0.07
    legate
    0.07
    .week
    0.07
    _SUB
    0.07
     Set
    0.07
    -note
    0.07
    _agent
    0.07
    .delivery
    0.06
    Act Density 0.032%

    No Known Activations