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

    Neuronpedia

    INDEX
    Explanations

    you can

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Cap
    1.13
    Cap
    1.10
    ASK
    1.05
     cap
    1.05
     Caps
    1.05
    샨
    1.01
     Chuk
    0.98
    Bas
    0.95
     CAP
    0.94
    fordern
    0.93
    POSITIVE LOGITS
    ->
    1.65
     ->
    1.40
    ()->
    0.91
    ::
    0.88
    ]->
    0.88
    -->
    0.87
     Myrtle
    0.86
    ->_
    0.83
    _->
    0.81
    →
    0.81
    Act Density 0.282%

    No Known Activations