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

    Neuronpedia

    INDEX
    Explanations

    Calendar

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Racing
    -0.07
    stim
    -0.07
    ragments
    -0.07
    (hostname
    -0.06
     \↵
    -0.06
     영어
    -0.06
     $↵
    -0.06
    -self
    -0.06
    代
    -0.06
     flowers
    -0.06
    POSITIVE LOGITS
    .rt
    0.06
    �로
    0.06
    ائج
    0.06
    .xx
    0.06
    .shadow
    0.06
     خلال
    0.06
    “If
    0.06
     shel
    0.06
     cloves
    0.06
    PrivateKey
    0.06
    Act Density 0.000%

    No Known Activations