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

    Neuronpedia

    INDEX
    Explanations

    "make up" phrase

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     extingu
    -0.06
     Flower
    -0.06
    ialog
    -0.06
    علام
    -0.06
     memoria
    -0.06
    ายใน
    -0.06
     disobed
    -0.06
     지원
    -0.06
    /image
    -0.06
    .lt
    -0.06
    POSITIVE LOGITS
    ΟΜ
    0.07
     quarterly
    0.07
     bson
    0.07
    .getPassword
    0.06
     SimpleDateFormat
    0.06
     commit
    0.06
     applications
    0.06
     BP
    0.06
    ][$
    0.06
    -third
    0.06
    Act Density 0.020%

    No Known Activations