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

    Neuronpedia

    INDEX
    Explanations

    incidence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Dé
    -0.07
    gorit
    -0.07
    -learning
    -0.07
    �
    -0.06
    ets
    -0.06
     initiatives
    -0.06
     abc
    -0.06
     palindrome
    -0.06
    (enable
    -0.06
    abilit
    -0.06
    POSITIVE LOGITS
     Albania
    0.07
    .Merge
    0.07
     Hands
    0.07
     perimeter
    0.06
     مارس
    0.06
     karakter
    0.06
    	CHECK
    0.06
    ですが
    0.06
     Prescott
    0.06
     شدند
    0.06
    Act Density 0.238%

    No Known Activations