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

    Neuronpedia

    INDEX
    Explanations

    who or that followed by verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     лишь
    0.93
    э
    0.86
     মধ্যেও
    0.81
     বেশকিছু
    0.81
    за
    0.78
    ablement
    0.78
    жа
    0.77
     એક
    0.77
     reveló
    0.77
    у
    0.76
    POSITIVE LOGITS
    soever
    0.88
    mg
    0.84
    ms
    0.79
     العربيه
    0.79
    ser
    0.78
    m
    0.77
     Dazu
    0.77
    larda
    0.75
    muse
    0.75
     transpired
    0.74
    Act Density 0.151%

    No Known Activations