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

    Neuronpedia

    INDEX
    Explanations

    unlock design process

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     biographer
    0.93
     Variant
    0.86
     Tunnel
    0.81
     biography
    0.77
     Biography
    0.76
     Interpreter
    0.76
     Archae
    0.75
     Hints
    0.74
     Game
    0.72
     adaptation
    0.72
    POSITIVE LOGITS
     preocupaciones
    1.55
    esehatan
    1.53
     bothering
    1.52
     urgente
    1.50
     worrisome
    1.50
     enforceable
    1.48
     hardworking
    1.47
     demandas
    1.46
     intolerable
    1.45
     questões
    1.45
    Act Density 0.637%

    No Known Activations