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

    Neuronpedia

    INDEX
    Explanations

    technical specifications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     activity
    -0.08
    FullPath
    -0.07
     spotted
    -0.06
    itemName
    -0.06
    _managed
    -0.06
     texting
    -0.06
     GOT
    -0.06
    activity
    -0.06
    mmas
    -0.06
     delete
    -0.06
    POSITIVE LOGITS
     educate
    0.07
     Harry
    0.07
    ATOM
    0.06
     ceil
    0.06
    rose
    0.06
    ['__
    0.06
    Mark
    0.06
    (nb
    0.06
    (cr
    0.06
    Mr
    0.06
    Act Density 0.029%

    No Known Activations