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

    Neuronpedia

    INDEX
    Explanations

    research studies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    야
    -0.07
    -feature
    -0.07
    /m
    -0.06
     Γκ
    -0.06
     vé
    -0.06
    FirstOrDefault
    -0.06
     DAG
    -0.06
    _pci
    -0.06
    ifty
    -0.06
     KeyValuePair
    -0.06
    POSITIVE LOGITS
    asyon
    0.06
     enclosing
    0.06
    ialias
    0.06
    cker
    0.06
    ieri
    0.06
    .sf
    0.06
    topics
    0.06
    жения
    0.06
    aciente
    0.06
    قلال
    0.06
    Act Density 0.117%

    No Known Activations