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

    Neuronpedia

    INDEX
    Explanations

    a an

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     disagrees
    -0.07
    都说
    -0.07
    -E
    -0.07
     Asians
    -0.07
     furious
    -0.07
     GP
    -0.07
     ×
    -0.06
    iran
    -0.06
    ído
    -0.06
     screaming
    -0.06
    POSITIVE LOGITS
    getStatus
    0.07
    くな
    0.07
    하였
    0.07
    .old
    0.07
    固定
    0.07
     setSize
    0.07
    钣
    0.06
    降雨
    0.06
    品味
    0.06
    卸
    0.06
    Act Density 0.194%

    No Known Activations