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

    Neuronpedia

    INDEX
    Explanations

    file paths and properties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     incidencia
    0.42
    ዞ
    0.39
     ctypes
    0.38
     sockfd
    0.38
    VERTEX
    0.37
     benzyl
    0.37
    वण्यात
    0.37
     फाइंड
    0.37
     heterod
    0.36
    кович
    0.36
    POSITIVE LOGITS
    getParent
    0.65
    getAbsolutePath
    0.63
    isFile
    0.62
    getName
    0.59
    Parent
    0.54
    mkdirs
    0.54
    isDirectory
    0.54
    absolute
    0.54
    Absolute
    0.54
     parent
    0.52
    Act Density 0.005%

    No Known Activations