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

    Neuronpedia

    INDEX
    Explanations

    steps add noise

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    in
    0.51
    ли
    0.46
    conditions
    0.45
     prosecutions
    0.45
    methylation
    0.45
    lications
    0.44
    э
    0.44
    ಲ್ಲಿ
    0.43
     наличии
    0.43
    isIn
    0.42
    POSITIVE LOGITS
     lacer
    0.47
     argent
    0.46
     Alternate
    0.46
     Linkedin
    0.46
     polymer
    0.44
     Geometry
    0.44
     Rail
    0.44
     rake
    0.44
     LinkedIn
    0.43
     Musical
    0.43
    Act Density 0.002%

    No Known Activations