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

    Neuronpedia

    INDEX
    Explanations

    other

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (play
    -0.07
     primitive
    -0.07
     emphasized
    -0.07
     promoted
    -0.07
     M
    -0.06
     ineff
    -0.06
    ucus
    -0.06
     purification
    -0.06
     Z
    -0.06
     如
    -0.06
    POSITIVE LOGITS
    ollider
    0.07
    토토
    0.07
     Mig
    0.06
    」（
    0.06
    overy
    0.06
     खबर
    0.06
    .character
    0.06
    _receipt
    0.06
    ήν
    0.06
    �
    0.06
    Act Density 0.013%

    No Known Activations