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

    Neuronpedia

    INDEX
    Explanations

    highly positive emotional reviews

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    http
    0.52
     http
    0.52
     अपेक्षाकृत
    0.46
     utilitarian
    0.45
     easy
    0.44
     sturdy
    0.43
    엷
    0.43
    ;:
    0.43
     understated
    0.43
    ใช้ง
    0.43
    POSITIVE LOGITS
    🫶
    1.00
    🥹
    0.96
    🥰
    0.95
     🥰
    0.93
    🥳
    0.86
    🤩
    0.82
    🩷
    0.80
    🫠
    0.79
    🥺
    0.77
    🥵
    0.75
    Act Density 0.000%

    No Known Activations