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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     {}↵↵
    -0.07
     blazing
    -0.06
     ids
    -0.06
     {}↵
    -0.06
     podporu
    -0.06
    řejmě
    -0.06
    霞
    -0.06
     ella
    -0.06
     fals
    -0.06
     boil
    -0.06
    POSITIVE LOGITS
    /board
    0.06
     supplementary
    0.06
    】,
    0.06
     rigid
    0.06
    (block
    0.06
    voie
    0.06
     Supplementary
    0.06
    -init
    0.06
     hairy
    0.06
     Advertisement
    0.06
    Act Density 0.205%

    No Known Activations