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

    Neuronpedia

    INDEX
    Explanations

    .Bundle

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     incremented
    -0.07
    �
    -0.07
     ε�
    -0.06
    *'
    -0.06
    ﾞ
    -0.06
    áj
    -0.06
     венти
    -0.06
     الذه
    -0.06
     woo
    -0.06
     pov
    -0.06
    POSITIVE LOGITS
     stacks
    0.06
     Abyss
    0.06
     burst
    0.06
    .Router
    0.06
    .Packet
    0.06
     never
    0.06
    """↵
    0.06
    .hist
    0.06
    �
    0.06
     ш
    0.06
    Act Density 0.001%

    No Known Activations