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

    Neuronpedia

    INDEX
    Explanations

    racially charged, ship, slave

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ச
    0.69
    ক
    0.68
     undivided
    0.66
    َ
    0.66
     obstruct
    0.63
    क
    0.61
    یک
    0.60
    ים
    0.60
     incluso
    0.59
    みの
    0.59
    POSITIVE LOGITS
    ar
    0.86
    city
    0.67
    gym
    0.67
    KE
    0.66
    proble
    0.66
    death
    0.64
    tourism
    0.64
    school
    0.64
    eu
    0.64
    ulan
    0.64
    Act Density 0.000%

    No Known Activations