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

    Neuronpedia

    INDEX
    Explanations

    email

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _CL
    -0.07
    .region
    -0.06
     relaxing
    -0.06
     operatives
    -0.06
    しの
    -0.06
     greedy
    -0.06
     psychedelic
    -0.06
    ou
    -0.06
     รวม
    -0.06
    _FRONT
    -0.06
    POSITIVE LOGITS
     sınav
    0.07
    스템
    0.07
    aspers
    0.07
     Dagger
    0.07
    (df
    0.07
     тип
    0.06
    _slide
    0.06
     economics
    0.06
    ITERAL
    0.06
     접
    0.06
    Act Density 0.005%

    No Known Activations