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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    enderror
    -0.56
    RunWith
    -0.54
    aronder
    -0.50
     igång
    -0.49
    ValueStyle
    -0.49
    lijks
    -0.49
     säll
    -0.48
     тонн
    -0.45
     fleste
    -0.44
     لديك
    -0.44
    POSITIVE LOGITS
     irradiation
    0.60
     PyLong
    0.59
    queryInterface
    0.58
     Loth
    0.57
    "])
    0.57
    brainly
    0.56
     muualla
    0.56
     imageUrl
    0.54
    CDCl
    0.54
     signal
    0.52
    Act Density 0.001%

    No Known Activations