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

    Neuronpedia

    INDEX
    Explanations

    Classification categories

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     TAS
    -0.07
     reportedly
    -0.07
     desires
    -0.07
     tk
    -0.07
    Asc
    -0.07
    ification
    -0.07
     repeatedly
    -0.07
    شار
    -0.06
    -job
    -0.06
    Match
    -0.06
    POSITIVE LOGITS
    猫
    0.07
     bör
    0.06
     statewide
    0.06
     أص
    0.06
    InvalidOperationException
    0.06
    下载
    0.06
    ayd
    0.06
     advertis
    0.06
     pornografia
    0.06
     değ
    0.06
    Act Density 0.003%

    No Known Activations