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

    Neuronpedia

    INDEX
    Explanations

    laying/laid

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ms
    0.73
     unless
    0.72
    me
    0.72
    mt
    0.70
    giv
    0.67
    .`);
    0.65
     icin
    0.65
    arlos
    0.65
    fors
    0.65
    Vm
    0.64
    POSITIVE LOGITS
     supermarkets
    0.92
     invertebrates
    0.91
     restaurante
    0.89
     restaurants
    0.85
     nightclubs
    0.84
    企业
    0.84
     functors
    0.84
     phylogenetic
    0.83
     tokamaks
    0.83
     cryptocur
    0.82
    Act Density 0.001%

    No Known Activations