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

    Neuronpedia

    INDEX
    Explanations

    Space colonization

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .getvalue
    -0.07
    urther
    -0.07
    ༕
    -0.07
    ивают
    -0.07
    andard
    -0.07
    ază
    -0.06
    反映
    -0.06
     ACCOUNT
    -0.06
    🕴
    -0.06
    .jar
    -0.06
    POSITIVE LOGITS
    |M
    0.07
    בר
    0.07
    卫
    0.07
    WithError
    0.07
    술
    0.07
     ep
    0.06
    异
    0.06
     Cum
    0.06
    辉煌
    0.06
    הק
    0.06
    Act Density 0.022%

    No Known Activations