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

    Neuronpedia

    INDEX
    Explanations

    HTML titles and project configuration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mulch
    0.59
    ម្ល
    0.39
     vrchol
    0.38
    ˛
    0.38
    ُر
    0.38
    銓
    0.37
     titer
    0.37
    畦
    0.36
     titre
    0.36
     ht
    0.36
    POSITIVE LOGITS
    Project
    0.50
    JavaScript
    0.50
    ProjectType
    0.48
    Sonar
    0.45
     PSP
    0.44
    RootManager
    0.44
     Project
    0.43
    Vcs
    0.42
    sonar
    0.42
    Cpp
    0.40
    Act Density 0.001%

    No Known Activations