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

    Neuronpedia

    INDEX
    Explanations

    Ember

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Holding
    -0.07
    达到
    -0.07
     �
    -0.07
     moins
    -0.06
     natural
    -0.06
    �
    -0.06
     объяс
    -0.06
     Pitt
    -0.06
     Walt
    -0.06
    gerald
    -0.06
    POSITIVE LOGITS
     Ember
    0.12
     ember
    0.09
    ember
    0.08
    Em
    0.08
    .er
    0.07
    Summer
    0.07
    orable
    0.07
    BER
    0.07
    ober
    0.07
    ER
    0.06
    Act Density 0.001%

    No Known Activations