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

    Neuronpedia

    INDEX
    Explanations

    common prefixes in code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     testes
    0.36
    །
    0.34
    Github
    0.32
    ྕ
    0.32
     communists
    0.31
     이미지
    0.31
     соеди
    0.31
     myCamera
    0.31
     addons
    0.30
     التعامل
    0.30
    POSITIVE LOGITS
    aré
    0.42
    key
    0.38
    arsk
    0.38
    kových
    0.36
    etown
    0.36
    är
    0.35
    lers
    0.35
    ersburg
    0.35
    ker
    0.35
    ář
    0.35
    Act Density 0.001%

    No Known Activations