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

    Neuronpedia

    INDEX
    Explanations

    negative emotions and challenges

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Nancy
    -1.08
     velours
    -1.06
    isierung
    -1.04
    getMenuInflater
    -1.02
    formatie
    -1.02
    -1.00
    fifth
    -1.00
     logica
    -1.00
     cuartos
    -0.99
    ª
    -0.99
    POSITIVE LOGITS
     then
    1.34
     at
    1.28
     бывают
    1.05
     trochę
    0.98
    Politique
    0.96
     not
    0.96
     later
    0.93
     sometimes
    0.93
     especias
    0.90
    を守る
    0.90
    Act Density 0.104%

    No Known Activations