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

    Neuronpedia

    INDEX
    Explanations

    but however here basically

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    트워크
    0.83
    on
    0.78
    MBOL
    0.77
    ]++;
    0.75
    '];
    0.75
     강조
    0.75
     lũ
    0.75
    .¹
    0.74
    ]})
    0.74
    ])))
    0.74
    POSITIVE LOGITS
     Ants
    0.88
     esters
    0.87
    मा
    0.86
     cantidad
    0.86
     residences
    0.84
    punyai
    0.83
     pharmacies
    0.83
    వారి
    0.83
     landslides
    0.83
     countries
    0.82
    Act Density 0.016%

    No Known Activations