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

    Neuronpedia

    INDEX
    Explanations

    Las

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     คล
    -0.08
     appealing
    -0.07
     new
    -0.07
    biology
    -0.07
     constitution
    -0.07
     stories
    -0.07
    .^
    -0.06
     semantics
    -0.06
    Project
    -0.06
     nei
    -0.06
    POSITIVE LOGITS
     Las
    0.07
     tamam
    0.07
    ds
    0.06
     lazy
    0.06
     Das
    0.06
     Rope
    0.06
    ila
    0.06
    акон
    0.06
    atching
    0.06
    εκ
    0.06
    Act Density 0.047%

    No Known Activations