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

    Neuronpedia

    INDEX
    Explanations

    the [noun]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     полуо
    1.20
    }^{*}\
    1.17
    هما
    1.16
    чается
    1.13
    ه
    1.13
     ২০২০
    1.13
    ваете
    1.13
    ല
    1.13
     какая
    1.11
     ronda
    1.11
    POSITIVE LOGITS
    ci
    1.37
    gn
    1.19
    a
    1.15
    to
    1.10
     This
    1.09
    ktion
    1.08
     contribuer
    1.06
    ve
    1.05
    configuration
    1.05
    ri
    1.03
    Act Density 0.007%

    No Known Activations