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

    Neuronpedia

    INDEX
    Explanations

    configuration parameters and assignments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Best
    0.52
    ist
    0.50
    Best
    0.46
     Help
    0.46
     Mu
    0.46
     Voice
    0.46
     Tek
    0.45
     Single
    0.44
     Tab
    0.44
    atek
    0.44
    POSITIVE LOGITS
    鯱
    0.49
    itato
    0.46
     purporting
    0.45
     donning
    0.45
     rupp
    0.44
    edown
    0.44
    ү
    0.44
     옮
    0.44
    ख्य
    0.43
     riparian
    0.43
    Act Density 0.000%

    No Known Activations