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

    Neuronpedia

    INDEX
    Explanations

    no access to google search

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ar
    0.41
     Re
    0.40
    PAUL
    0.39
     Tidal
    0.39
     Paul
    0.38
     प्रवाह
    0.38
    paul
    0.37
     PAUL
    0.37
    ostí
    0.36
     Forrester
    0.35
    POSITIVE LOGITS
    Victoria
    0.44
    Oz
    0.39
     oz
    0.39
    victoria
    0.38
     оз
    0.38
    oz
    0.36
    treasure
    0.36
    уре
    0.36
    fri
    0.36
     Jarrett
    0.36
    Act Density 0.007%

    No Known Activations