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

    Neuronpedia

    INDEX
    Explanations

    names starting with Nico or Niko

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     वन
    0.41
     Presentation
    0.41
     Presentations
    0.41
    Bankr
    0.40
    ávan
    0.40
    čních
    0.40
    vection
    0.39
    ursive
    0.39
    क्लेव
    0.39
     जागरूकता
    0.38
    POSITIVE LOGITS
     Rosberg
    0.41
     implied
    0.41
    ଲା
    0.41
     paired
    0.38
     Peker
    0.37
    Mar
    0.37
     Hul
    0.37
    Apl
    0.36
    LA
    0.36
    Pour
    0.36
    Act Density 0.004%

    No Known Activations