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

    Neuronpedia

    INDEX
    Explanations

    forms of to be followed by state

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     became
    0.93
     came
    0.79
     remained
    0.77
     overtook
    0.77
     becomes
    0.75
     clarify
    0.75
     furnishes
    0.75
     gave
    0.74
    became
    0.74
     remains
    0.74
    POSITIVE LOGITS
     tantamount
    1.08
     equivalent
    1.05
    equivalent
    0.90
    Equivalent
    0.90
     undoubtedly
    0.88
     fraught
    0.88
     still
    0.86
     equivalente
    0.86
     cũng
    0.86
     very
    0.85
    Act Density 0.009%

    No Known Activations