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

    Neuronpedia

    INDEX
    Explanations

    future/will

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     is
    -1.38
     are
    -1.18
     has
    -1.01
     was
    -0.89
     कहते
    -0.84
     presentará
    -0.80
     does
    -0.79
     者
    -0.75
    (_)
    -0.75
     उन्होंने
    -0.74
    POSITIVE LOGITS
    nessione
    0.88
    ould
    0.86
    dracht
    0.83
    pragma
    0.82
     sẽ
    0.80
     başlay
    0.79
    Shall
    0.79
    shall
    0.79
    paraíso
    0.78
    Will
    0.77
    Act Density 0.012%

    No Known Activations