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

    Neuronpedia

    INDEX
    Explanations

    implementing actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cambiando
    0.44
     poniendo
    0.39
     aplicando
    0.39
     entrando
    0.38
     giocando
    0.37
     explicando
    0.37
     tornando
    0.37
     caminando
    0.36
     viviendo
    0.36
    ানো
    0.36
    POSITIVE LOGITS
     create
    0.95
     execute
    0.95
     participate
    0.95
     communicate
    0.95
     engage
    0.93
     provide
    0.92
     integrate
    0.92
     establish
    0.91
     pursue
    0.91
     generate
    0.90
    Act Density 0.367%

    No Known Activations