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

    Neuronpedia

    INDEX
    Explanations

    prepositions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    PerformLayout
    -0.59
    complexContent
    -0.58
    enschappelijke
    -0.56
    ptonshire
    -0.55
    AppMethodBeat
    -0.55
     initComponents
    -0.54
    CreateModel
    -0.50
    Identyfik
    -0.48
    jiet
    -0.47
    droj
    -0.47
    POSITIVE LOGITS
     computing
    0.75
     writing
    0.69
     deriving
    0.65
     coming
    0.61
     dAtA
    0.57
     proving
    0.57
     dedu
    0.57
     decom
    0.56
    transQ
    0.56
    TagMode
    0.55
    Act Density 0.032%

    No Known Activations