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

    Neuronpedia

    INDEX
    Explanations

    legal documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     defaultValue
    -0.07
    аток
    -0.07
     하루
    -0.06
    .Upload
    -0.06
     restroom
    -0.06
     прек
    -0.06
    ytut
    -0.06
     emoc
    -0.06
     Kor
    -0.06
    Syntax
    -0.06
    POSITIVE LOGITS
     PUS
    0.06
    .commons
    0.06
     refriger
    0.06
     keeps
    0.06
    itious
    0.06
     cushion
    0.06
    roleum
    0.06
     Sustainable
    0.06
    rai
    0.06
    ONG
    0.06
    Act Density 0.020%

    No Known Activations