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

    Neuronpedia

    INDEX
    Explanations

    academic abstracts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ท
    -0.07
    omega
    -0.07
     '?'
    -0.06
     Dalton
    -0.06
     Airlines
    -0.06
     biệt
    -0.06
    (agent
    -0.06
     MessageType
    -0.06
     Widow
    -0.06
    atör
    -0.06
    POSITIVE LOGITS
    511
    0.06
    classifier
    0.06
     monitored
    0.06
     }]↵
    0.06
    595
    0.06
     reconstruct
    0.06
    参照
    0.06
    чає
    0.06
    (host
    0.06
    �프
    0.06
    Act Density 0.023%

    No Known Activations