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

    Neuronpedia

    INDEX
    Explanations

    over

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sei
    -0.07
    quisites
    -0.06
    řiv
    -0.06
    aurus
    -0.06
    альному
    -0.06
     nouveaux
    -0.06
    (pred
    -0.06
    lerinden
    -0.06
     welfare
    -0.06
    \Traits
    -0.06
    POSITIVE LOGITS
     sacrificing
    0.07
     Vinyl
    0.07
    asion
    0.07
    inium
    0.07
    лика
    0.07
    ения
    0.06
    丶
    0.06
    ative
    0.06
    mazon
    0.06
     admired
    0.06
    Act Density 0.000%

    No Known Activations