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
     suggestive
    -0.08
    _SOL
    -0.07
    positions
    -0.07
    "))↵↵
    -0.07
     scenarios
    -0.07
     regression
    -0.07
    <=
    -0.06
    Hand
    -0.06
    );\↵
    -0.06
     Muslims
    -0.06
    POSITIVE LOGITS
     Coinbase
    0.07
     grâce
    0.06
     happiest
    0.06
    =index
    0.06
     объ
    0.06
    635
    0.06
     EntryPoint
    0.06
    ическая
    0.06
    /Object
    0.06
    Τ
    0.06
    Act Density 0.010%

    No Known Activations