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

    Neuronpedia

    INDEX
    Explanations

    phone devices

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    listen
    -0.07
    software
    -0.06
    Credentials
    -0.06
     oil
    -0.06
    Hal
    -0.06
    Beer
    -0.06
    Miami
    -0.06
    records
    -0.06
    อาร
    -0.06
    Bubble
    -0.06
    POSITIVE LOGITS
     XT
    0.07
     chunk
    0.07
     Increment
    0.06
     Fou
    0.06
    (simp
    0.06
     пласти
    0.06
    肃
    0.06
     cậu
    0.06
    шается
    0.06
    zhou
    0.06
    Act Density 0.014%

    No Known Activations