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

    Neuronpedia

    INDEX
    Explanations

    as

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     '.
    -0.06
    .ap
    -0.06
    Miss
    -0.06
     Frozen
    -0.06
    经营
    -0.06
     Buck
    -0.06
     abilities
    -0.06
    _Filter
    -0.06
     張
    -0.06
    ]]↵↵
    -0.06
    POSITIVE LOGITS
     generosity
    0.07
    UREMENT
    0.07
     adequ
    0.06
     piè
    0.06
     flu
    0.06
    短
    0.06
    ONSE
    0.06
     ل
    0.06
     حذ
    0.06
    VertexAttribArray
    0.06
    Act Density 0.039%

    No Known Activations