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

    Neuronpedia

    INDEX
    Explanations

    open macOS applications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WE
    0.40
     manifest
    0.38
    صال
    0.37
     armado
    0.37
    tensorflow
    0.37
    ANCED
    0.37
     tooling
    0.36
    PTR
    0.36
     Webs
    0.36
    Zy
    0.35
    POSITIVE LOGITS
     Finder
    0.71
     Spotlight
    0.70
     Mac
    0.68
     Macs
    0.66
     mac
    0.63
    Mac
    0.63
    Finder
    0.63
     파인더
    0.60
     finder
    0.58
     spotlight
    0.57
    Act Density 0.014%

    No Known Activations