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

    Neuronpedia

    INDEX
    Explanations

    state

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     TB
    -0.07
     lx
    -0.06
     kde
    -0.06
     iets
    -0.06
     MCS
    -0.06
     spéc
    -0.06
    decor
    -0.06
     Poetry
    -0.06
    KN
    -0.06
    _LINEAR
    -0.06
    POSITIVE LOGITS
     distributor
    0.07
     dorsal
    0.07
    (flags
    0.07
    Connect
    0.06
    UMAN
    0.06
     every
    0.06
    InstanceState
    0.06
    _EXTERNAL
    0.06
     smarty
    0.06
     States
    0.06
    Act Density 0.015%

    No Known Activations