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

    Neuronpedia

    INDEX
    Explanations

    places, travel

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    L
    0.71
    стта
    0.71
    в
    0.71
    о
    0.70
    NMR
    0.68
    вчи
    0.67
    во
    0.67
    кса
    0.66
    и
    0.65
    ста
    0.65
    POSITIVE LOGITS
     wooden
    1.01
     deal
    0.99
     sleeping
    0.98
     grinder
    0.94
     put
    0.94
     enrichment
    0.94
     Kh
    0.91
     trip
    0.91
     phosphate
    0.91
     call
    0.91
    Act Density 0.000%

    No Known Activations