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

    Neuronpedia

    INDEX
    Explanations

    formal project descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ity
    -0.06
    ,null
    -0.06
     contempt
    -0.06
    -management
    -0.06
     Multiply
    -0.06
    .Parcelable
    -0.06
    ");↵↵↵
    -0.06
     Market
    -0.06
     stature
    -0.06
     assurance
    -0.06
    POSITIVE LOGITS
    hoa
    0.07
     вне
    0.07
    anan
    0.07
     slun
    0.06
    ्वर
    0.06
    Pl
    0.06
     кожного
    0.06
     Voice
    0.06
    λλ
    0.06
    编辑
    0.06
    Act Density 0.077%

    No Known Activations