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

    Neuronpedia

    INDEX
    Explanations

    legal court documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    depends
    -0.07
     Fem
    -0.07
    ều
    -0.07
    잠
    -0.07
    .transfer
    -0.07
     commend
    -0.06
     категор
    -0.06
     chores
    -0.06
     stale
    -0.06
     Important
    -0.06
    POSITIVE LOGITS
    ➮
    0.07
    notin
    0.07
    NAL
    0.07
     Tw
    0.07
    0.06
    طبيع
    0.06
    otype
    0.06
    ISM
    0.06
     الديمقرا
    0.06
    ☳
    0.06
    Act Density 0.000%

    No Known Activations