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
     этот
    -0.07
     mất
    -0.07
    .OR
    -0.06
     HOL
    -0.06
    862
    -0.06
    .SUB
    -0.06
    fft
    -0.06
     transf
    -0.06
    IOC
    -0.06
     عشق
    -0.06
    POSITIVE LOGITS
     různých
    0.07
     Rid
    0.07
    (opt
    0.06
     banner
    0.06
     bone
    0.06
     Scott
    0.06
    bond
    0.06
    _Right
    0.06
    WSC
    0.06
     Angeles
    0.06
    Act Density 0.042%

    No Known Activations