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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     attack
    -0.07
    eventId
    -0.07
     Hydra
    -0.07
    attack
    -0.06
    CLUSION
    -0.06
    _NC
    -0.06
     Rück
    -0.06
     (),
    -0.06
    ẵ
    -0.06
    авлива
    -0.06
    POSITIVE LOGITS
     terminates
    0.07
     sucht
    0.07
     Guard
    0.07
    tracts
    0.07
     dei
    0.06
     porte
    0.06
     combin
    0.06
    last
    0.06
     cooperating
    0.06
    Customers
    0.06
    Act Density 0.000%

    No Known Activations