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

    Neuronpedia

    INDEX
    Explanations

    dite

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    throat
    -0.77
    lating
    -0.76
    lation
    -0.73
    chloric
    -0.70
    lations
    -0.69
    olia
    -0.66
    lates
    -0.63
     representation
    -0.62
     throat
    -0.61
    lated
    -0.59
    POSITIVE LOGITS
    Kjelder
    0.76
     Turquie
    0.56
    ⓘ
    0.54
    ViewImports
    0.54
    الإنجليزية
    0.51
    MessageInfo
    0.50
    かし
    0.50
    BagLayout
    0.50
    AutoScaleMode
    0.49
     Hongrie
    0.49
    Act Density 0.051%

    No Known Activations