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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Cap
    -0.08
    Ｂ
    -0.07
    .*↵↵
    -0.07
    .=
    -0.07
    enville
    -0.07
     Modify
    -0.07
    ……”↵↵
    -0.07
    ……”
    -0.07
    бирать
    -0.07
     Backup
    -0.07
    POSITIVE LOGITS
     reportedly
    0.11
     (?)
    0.09
     famously
    0.09
     chief
    0.08
    (?)
    0.08
     starvation
    0.08
     officially
    0.07
     deception
    0.07
     Jaguar
    0.07
    rovers
    0.07
    Act Density 0.066%

    No Known Activations