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

    Neuronpedia

    INDEX
    Explanations

    output

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Crom
    -0.06
     ja
    -0.06
    าน
    -0.06
    污
    -0.06
     thereafter
    -0.06
    ォ
    -0.06
    (pi
    -0.06
     gp
    -0.06
    .Clone
    -0.06
    цями
    -0.06
    POSITIVE LOGITS
     mercado
    0.07
    ไซต
    0.07
     hilarious
    0.06
     Auto
    0.06
     инвести
    0.06
    精神
    0.06
     菲律宾
    0.06
     WARRANTY
    0.06
     humano
    0.06
    τικο
    0.06
    Act Density 0.006%

    No Known Activations