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

    Neuronpedia

    INDEX
    Explanations

    relationships/feelings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .parts
    -0.07
     Ihr
    -0.07
     outsourcing
    -0.07
    希
    -0.06
     stderr
    -0.06
    .mc
    -0.06
     önemli
    -0.06
     필요한
    -0.06
    mutex
    -0.06
    oward
    -0.06
    POSITIVE LOGITS
     legitim
    0.07
     trader
    0.06
     chaining
    0.06
    .tokenize
    0.06
     Iranian
    0.06
     exploded
    0.06
    ,key
    0.06
    flammatory
    0.06
     waste
    0.06
     ISA
    0.06
    Act Density 0.029%

    No Known Activations