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

    Neuronpedia

    INDEX
    Explanations

    aggressive dialogue

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Propagation
    -0.07
     ICE
    -0.07
    PUTE
    -0.07
    _SWAP
    -0.07
     icmp
    -0.07
    _neighbors
    -0.07
     Flatten
    -0.06
     Terrace
    -0.06
    мм
    -0.06
    Unfortunately
    -0.06
    POSITIVE LOGITS
    etermin
    0.07
    ‌گذ
    0.06
    플
    0.06
    (fixture
    0.06
     qualifier
    0.06
     qualifies
    0.06
     Strait
    0.05
     Accept
    0.05
     against
    0.05
     negocio
    0.05
    Act Density 0.078%

    No Known Activations