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

    Neuronpedia

    INDEX
    Explanations

    News articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Publishers
    -0.06
    :::
    -0.06
    onium
    -0.06
     LB
    -0.06
    (TM
    -0.06
    _df
    -0.06
     vowel
    -0.06
    聽
    -0.06
     tote
    -0.06
    producer
    -0.06
    POSITIVE LOGITS
     �
    0.07
    _ATOMIC
    0.07
    .Safe
    0.07
    uerdo
    0.06
    	cfg
    0.06
    	PORT
    0.06
    uration
    0.06
     segreg
    0.06
    perimental
    0.06
    -link
    0.06
    Act Density 0.041%

    No Known Activations