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

    Neuronpedia

    INDEX
    Explanations

    effectiveness

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     secure
    -0.07
     criminal
    -0.07
     day
    -0.06
    Sector
    -0.06
    -social
    -0.06
    pin
    -0.06
    ias
    -0.06
    modulo
    -0.06
    +i
    -0.06
    -bed
    -0.06
    POSITIVE LOGITS
     effectiveness
    0.09
     마법
    0.08
     �
    0.08
     کوه
    0.07
    _
↵
↵
    0.07
    ereum
    0.07
    кувати
    0.07
     triển
    0.07
    createForm
    0.07
     CROSS
    0.07
    Act Density 0.005%

    No Known Activations