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

    Neuronpedia

    INDEX
    Explanations

    Effectiveness evaluation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     capturing
    -0.07
     emperor
    -0.07
    猹
    -0.07
     dank
    -0.07
     parasite
    -0.07
    𝖌
    -0.07
    硬度
    -0.07
    chmod
    -0.06
     theolog
    -0.06
    -opacity
    -0.06
    POSITIVE LOGITS
     fifty
    0.08
     Hawkins
    0.07
    ستراتيجي
    0.07
     processing
    0.06
    Ҥ
    0.06
     Hussein
    0.06
     ?????
    0.06
     Jobs
    0.06
    aley
    0.06
     increasingly
    0.06
    Act Density 0.092%

    No Known Activations