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

    Neuronpedia

    INDEX
    Explanations

    configuration, narration, individual

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    /
    0.58
    '
    0.57
    -
    0.51
    @
    0.47
    ogram
    0.46
    ler
    0.42
     Jax
    0.42
     @
    0.42
    able
    0.41
     A
    0.40
    POSITIVE LOGITS
     інші
    0.49
    ва
    0.45
     शक्ति
    0.45
     інших
    0.44
     विरोध
    0.44
     रोकना
    0.44
     замеча
    0.43
     социа
    0.43
    다
    0.42
     कैंसर
    0.42
    Act Density 0.000%

    No Known Activations