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

    Neuronpedia

    INDEX
    Explanations

    name prefixes

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     trimester
    0.43
     `=`
    0.39
     factorial
    0.38
     VoIP
    0.38
     interrelated
    0.37
    <0x0E>
    0.37
    <0x10>
    0.37
     eLearning
    0.37
     ```
    0.37
     relational
    0.37
    POSITIVE LOGITS
     Ch
    0.46
     K
    0.44
     Sh
    0.38
     Mar
    0.38
     Ak
    0.38
     Al
    0.38
     Bar
    0.38
     Monastery
    0.38
    Ch
    0.37
     King
    0.36
    Act Density 0.122%

    No Known Activations