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

    Neuronpedia

    INDEX
    Explanations

    conjunctions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    इस
    -0.07
     王
    -0.07
     reaction
    -0.06
     shoulders
    -0.06
     elemento
    -0.06
    .'/
    -0.06
     Deadpool
    -0.06
    reaction
    -0.06
     marzo
    -0.06
    .setHorizontal
    -0.06
    POSITIVE LOGITS
     recall
    0.07
    小姐
    0.07
    >J
    0.07
    added
    0.07
     Herman
    0.07
     cinematic
    0.07
    ибли
    0.07
     recalling
    0.07
     anticipate
    0.07
    _added
    0.06
    Act Density 0.036%

    No Known Activations