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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Fruit
    -0.07
    parm
    -0.07
    ained
    -0.07
     distinguished
    -0.07
     lub
    -0.06
     men
    -0.06
    FORM
    -0.06
     customers
    -0.06
     Frank
    -0.06
     Kot
    -0.06
    POSITIVE LOGITS
    ための
    0.07
    (cps
    0.06
    avelength
    0.06
     ऐस
    0.06
     присутств
    0.06
    awi
    0.06
     的
    0.06
     germany
    0.06
    CHEMY
    0.06
    IGINAL
    0.06
    Act Density 0.093%

    No Known Activations