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
     en
    -0.07
    Meanwhile
    -0.07
    Democratic
    -0.07
    _PUSHDATA
    -0.07
     Vib
    -0.06
    AndFeel
    -0.06
     và
    -0.06
     přísluš
    -0.06
     probabil
    -0.06
     عراق
    -0.06
    POSITIVE LOGITS
    овые
    0.07
    ,))↵
    0.07
     babys
    0.06
           
    0.06
    .:
    0.06
    _CLUSTER
    0.06
    ….
    0.06
    .Car
    0.06
    ky
    0.06
    ')]
    0.06
    Act Density 0.018%

    No Known Activations