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

    Neuronpedia

    INDEX
    Explanations

    examples and context setting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     réfrig
    -1.05
     calentamiento
    -1.05
     thingy
    -1.04
     contemporain
    -1.03
    حداث
    -1.01
     apprehen
    -0.98
     penjara
    -0.97
    Completo
    -0.95
     numerosos
    -0.93
     auxquels
    -0.93
    POSITIVE LOGITS
    VALUE
    1.09
     condominium
    1.09
    licado
    1.09
    匿名使用者
    1.03
    ViewById
    1.03
    point
    1.02
    wikk
    1.02
     of
    1.02
    verifyException
    0.97
    λοι
    0.96
    Act Density 0.051%

    No Known Activations