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

    Neuronpedia

    INDEX
    Explanations

    code and legal text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     UNIT
    -0.07
     SPL
    -0.07
     ATA
    -0.07
     Lisa
    -0.07
     Sap
    -0.06
     harming
    -0.06
     Steve
    -0.06
     Rob
    -0.06
     Uz
    -0.06
     Az
    -0.06
    POSITIVE LOGITS
    yscale
    0.07
    licated
    0.07
    042
    0.06
    &view
    0.06
    pared
    0.06
     Μετα
    0.06
    -topic
    0.06
    MetaData
    0.06
     căn
    0.06
     coronary
    0.06
    Act Density 0.013%

    No Known Activations