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

    Neuronpedia

    INDEX
    Explanations

    develop

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     every
    -0.07
    隨
    -0.06
     relying
    -0.06
    جات
    -0.06
    混
    -0.06
     arising
    -0.06
    asyarakat
    -0.06
    ',↵
    -0.06
     pest
    -0.06
    arım
    -0.06
    POSITIVE LOGITS
    (retval
    0.06
    νοντας
    0.06
     elektrik
    0.06
     Operand
    0.06
     Weekend
    0.06
    sale
    0.06
      
    0.06
    pciones
    0.06
    rier
    0.06
    ,dim
    0.06
    Act Density 0.057%

    No Known Activations