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

    Neuronpedia

    INDEX
    Explanations

    falling in love

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    鍵
    0.41
    MINUTE
    0.38
     recept
    0.37
     বিটিআই
    0.37
     взаимодействия
    0.36
    ikey
    0.35
    ューズ
    0.35
     intimacy
    0.35
    ेच्छा
    0.35
    $.;
    0.35
    POSITIVE LOGITS
     enam
    1.30
     apaixon
    1.05
     mad
    1.02
     hopelessly
    0.94
     head
    0.86
     crazy
    0.83
     deeply
    0.82
     amoureux
    0.82
     falling
    0.81
     jatuh
    0.80
    Act Density 0.015%

    No Known Activations