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

    Neuronpedia

    INDEX
    Explanations

    code and data

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     commits
    -0.08
    assium
    -0.08
    戶
    -0.07
    体温
    -0.07
     neo
    -0.07
    .cli
    -0.07
    iosis
    -0.07
    phoneNumber
    -0.07
     iod
    -0.06
    コミュニケーション
    -0.06
    POSITIVE LOGITS
    _ACCEPT
    0.07
    >equals
    0.07
     informant
    0.07
    �
    0.07
     Played
    0.07
     upfront
    0.07
    Before
    0.07
     bez
    0.07
    _wrong
    0.06
    _preview
    0.06
    Act Density 0.043%

    No Known Activations