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

    Neuronpedia

    INDEX
    Explanations

    hunting

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Corpus
    -0.07
     smell
    -0.07
     abyss
    -0.07
     международ
    -0.07
    almost
    -0.07
    %↵↵
    -0.07
     Clayton
    -0.07
     가장
    -0.07
     divers
    -0.07
    Hook
    -0.06
    POSITIVE LOGITS
     atIndex
    0.06
    920
    0.06
    bread
    0.06
     NVIC
    0.06
     Ιω
    0.06
    &&!
    0.06
    manage
    0.05
    �
    0.05
     nev
    0.05
     třeba
    0.05
    Act Density 0.055%

    No Known Activations