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

    Neuronpedia

    INDEX
    Explanations

    build

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     yans
    -0.07
    煤
    -0.06
    �
    -0.06
    METHOD
    -0.06
    foobar
    -0.06
     Oh
    -0.06
     торгів
    -0.06
    ivityManager
    -0.06
     málo
    -0.06
     FOUND
    -0.06
    POSITIVE LOGITS
     restricting
    0.06
     analytic
    0.06
    _high
    0.06
     Choosing
    0.06
    )((
    0.06
    bay
    0.06
     Soc
    0.06
    _npc
    0.06
    oscopic
    0.06
    spiracy
    0.06
    Act Density 0.627%

    No Known Activations