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

    Neuronpedia

    INDEX
    Explanations

    trol de

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ville
    0.48
    Princeton
    0.44
    com
    0.43
    Republic
    0.43
    Shopping
    0.42
    Hospital
    0.41
    mir
    0.40
    산업
    0.40
    matic
    0.40
    Page
    0.39
    POSITIVE LOGITS
     sympathies
    0.53
    𝒔
    0.52
     нормы
    0.52
     कोणत्या
    0.51
     रस
    0.51
     unequiv
    0.50
     algebras
    0.50
     sympathize
    0.49
    )})$
    0.49
     amplitudes
    0.49
    Act Density 0.003%

    No Known Activations