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

    Neuronpedia

    INDEX
    Explanations

    offer something instead

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    unlike
    0.43
     বলেই
    0.43
    までは
    0.43
    Unlike
    0.41
    如果是
    0.41
    并不是
    0.40
     সবচে
    0.39
     наиболее
    0.39
     unlike
    0.38
    Imidazole
    0.38
    POSITIVE LOGITS
     instead
    2.70
    instead
    2.55
    Instead
    2.41
     вместо
    2.34
     Instead
    2.33
     invece
    2.22
     대신
    2.06
    代わりに
    2.03
     statt
    1.95
     zami
    1.70
    Act Density 0.036%

    No Known Activations