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

    Neuronpedia

    INDEX
    Explanations

    email/message excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     أنه
    -0.07
     Tooth
    -0.06
    _pel
    -0.06
    /ros
    -0.06
     intends
    -0.06
     VP
    -0.06
     cash
    -0.06
    _hz
    -0.06
    ราย
    -0.06
     kepada
    -0.06
    POSITIVE LOGITS
     Everywhere
    0.07
    _artist
    0.06
     Generates
    0.06
    creates
    0.06
    україн
    0.06
     tentative
    0.06
     Flatten
    0.06
     dropped
    0.06
    tone
    0.06
    /docker
    0.06
    Act Density 0.005%

    No Known Activations