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

    Neuronpedia

    INDEX
    Explanations

    clicking

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Literal
    -0.06
    elters
    -0.06
    alloc
    -0.06
    ajes
    -0.06
     RECEIVE
    -0.06
     Slo
    -0.06
     intestinal
    -0.06
    ーデ
    -0.06
    iare
    -0.06
     استرات
    -0.06
    POSITIVE LOGITS
     OMG
    0.07
     -->
↵
    0.07
     Fourth
    0.06
     defining
    0.06
     первой
    0.06
     Models
    0.06
    ㅋㅋ
    0.06
     according
    0.06
    Fourth
    0.06
    icontains
    0.06
    Act Density 0.002%

    No Known Activations