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

    Neuronpedia

    INDEX
    Explanations

    complex

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    UGC
    -0.08
     mười
    -0.07
     Arch
    -0.07
     Frozen
    -0.07
     Retro
    -0.07
     origins
    -0.07
     Babies
    -0.07
    &t
    -0.07
     setTimeout
    -0.07
    Meteor
    -0.07
    POSITIVE LOGITS
    阻
    0.07
     stringValue
    0.06
     discrim
    0.06
     denied
    0.06
    蚆
    0.06
     resizable
    0.06
    省公安
    0.06
    StatusCode
    0.06
     legalize
    0.06
    Son
    0.06
    Act Density 0.003%

    No Known Activations