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

    Neuronpedia

    INDEX
    Explanations

    rand

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Title
    -0.08
     comic
    -0.07
     ice
    -0.07
     polar
    -0.07
     possibile
    -0.07
     pus
    -0.07
    imore
    -0.06
    -system
    -0.06
     dubna
    -0.06
    -free
    -0.06
    POSITIVE LOGITS
    hardt
    0.07
     rand
    0.07
     stocking
    0.06
    保障
    0.06
     Rand
    0.06
     Shepard
    0.06
     Making
    0.06
     Ramsey
    0.06
    ourced
    0.06
     هستند
    0.06
    Act Density 0.003%

    No Known Activations