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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ,!
    -0.08
    -major
    -0.07
     là
    -0.07
    .join
    -0.07
    False
    -0.07
    ीदव
    -0.07
    	index
    -0.06
     oppress
    -0.06
    Subset
    -0.06
     Ott
    -0.06
    POSITIVE LOGITS
    follower
    0.06
    _LS
    0.06
    anst
    0.06
    amu
    0.06
     baş
    0.06
    /rs
    0.06
     �
    0.06
    рать
    0.06
    ⌒
    0.06
    outu
    0.06
    Act Density 0.019%

    No Known Activations