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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     méthode
    -0.07
    �
    -0.06
    Unsupported
    -0.06
    ораль
    -0.06
    -label
    -0.06
    BootApplication
    -0.06
     Therefore
    -0.06
    038
    -0.06
     菲律宾
    -0.06
     prim
    -0.06
    POSITIVE LOGITS
     mayo
    0.07
     refactor
    0.07
    	tab
    0.06
     eapply
    0.06
     abst
    0.06
     ulong
    0.06
    ują
    0.06
    istics
    0.06
     gadgets
    0.06
     fou
    0.06
    Act Density 0.016%

    No Known Activations