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
    -reader
    -0.07
     않
    -0.07
     erklärt
    -0.07
    市公安局
    -0.07
    ouden
    -0.07
     colonization
    -0.06
    早早
    -0.06
     Explosion
    -0.06
    卫视
    -0.06
     unsub
    -0.06
    POSITIVE LOGITS
     CURRENT
    0.08
     themselves
    0.08
    *****
↵
    0.07
    慢
    0.07
    weights
    0.07
    MING
    0.07
    机
    0.07
     puede
    0.07
    INPUT
    0.07
    hive
    0.07
    Act Density 0.003%

    No Known Activations