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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     disemb
    -0.06
     Blow
    -0.06
    376
    -0.06
     �
    -0.06
    excerpt
    -0.06
    `.↵
    -0.06
     �
    -0.06
    Remark
    -0.06
    ouis
    -0.06
     vodka
    -0.06
    POSITIVE LOGITS
     시간
    0.07
     UIGraphics
    0.07
    監督
    0.07
    ोफ
    0.06
     molding
    0.06
     materia
    0.06
    alking
    0.06
     محیط
    0.06
    ेदन
    0.06
    bruary
    0.06
    Act Density 0.020%

    No Known Activations