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

    Neuronpedia

    INDEX
    Explanations

    source folder and classpath

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     linemen
    0.44
    CommandBuffer
    0.42
     Philippe
    0.40
     laryng
    0.40
     defraud
    0.40
    DeviceCompliance
    0.40
    emort
    0.40
    েইল
    0.39
     alimony
    0.39
     touchpad
    0.39
    POSITIVE LOGITS
     roots
    0.57
     isTestSource
    0.57
     source
    0.57
    sourceFolder
    0.55
    roots
    0.54
     classpath
    0.54
     exploded
    0.52
     Source
    0.52
    Roots
    0.51
     Roots
    0.50
    Act Density 0.001%

    No Known Activations