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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    腦
    -0.07
    ;font
    -0.07
     akin
    -0.07
    threads
    -0.07
    .subplots
    -0.07
    onestly
    -0.06
    -most
    -0.06
     Occupy
    -0.06
     �
    -0.06
    ]%
    -0.06
    POSITIVE LOGITS
    INGS
    0.06
    ULLET
    0.06
    anner
    0.06
    ings
    0.06
    imus
    0.06
    พบ
    0.06
    Рµ
    0.06
    ，小
    0.06
    Buff
    0.06
     Proposal
    0.06
    Act Density 0.149%

    No Known Activations